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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to various topics

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

    Questions followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    questions following colons or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    -0.61
     mel
    -0.57
     you
    -0.56
     The
    -0.55
     the
    -0.55
     he
    -0.50
     neither
    -0.50
    neo
    -0.48
     we
    -0.48
    一面
    -0.47
    POSITIVE LOGITS
    abestanden
    0.81
    findpost
    0.78
     beginnetje
    0.76
     Audiodateien
    0.76
    MENAFN
    0.73
     initComponents
    0.72
     nahilalakip
    0.70
     saites
    0.69
    ⓧ
    0.69
    astéroïdes
    0.69
    Act Density 0.174%

    No Known Activations