Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tokens or symbols associated with sections or formatting in code and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, numbers and symbols

    np_acts-logits-general · gemini-2.0-flash

    separators and dividers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ────────
    -0.84
    ════════
    -0.76
    ================
    -0.74
    ▬▬▬▬▬▬▬▬
    -0.73
    %%%%%%%%%%%%%%%%
    -0.71
    ################
    -0.69
    ────
    -0.64
    ----------------
    -0.62
    ————————————————
    -0.62
    IContainer
    -0.61
    POSITIVE LOGITS
    !*\
    0.76
     Arjuna
    0.69
    _.
    0.61
    orianCalendar
    0.58
     CURIAM
    0.58
    astéroïdes
    0.56
    Spacer
    0.56
     InputDecoration
    0.56
    分割
    0.54
    utnik
    0.54
    Act Density 0.280%

    No Known Activations