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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs related to modes or states

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

    computing mode or file mode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PYX
    -0.55
    delwed
    -0.44
     שוליים
    -0.42
    EndProject
    -0.41
    Oph
    -0.39
    ʐ
    -0.37
    StatusBadRequest
    -0.37
     allarg
    -0.36
    varlak
    -0.36
    essere
    -0.35
    POSITIVE LOGITS
    Mode
    2.81
     Mode
    2.30
    MODE
    1.84
     mode
    1.73
     MODE
    1.72
     Modes
    1.61
    mode
    1.57
    Modes
    1.51
    setMode
    1.47
     modes
    1.40
    Act Density 0.004%

    No Known Activations