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

    Neuronpedia

    INDEX
    Explanations

    sequences of code execution or output statements

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

    Python interactive prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.64
     مشين
    -0.59
     numberWith
    -0.58
     Савезне
    -0.57
    fjspx
    -0.57
    ReusableCell
    -0.54
    erals
    -0.51
    Packard
    -0.49
    enderror
    -0.49
    ICOLON
    -0.48
    POSITIVE LOGITS
    >>>
    2.31
     >>>
    1.67
    >>>>>
    1.25
    >>>>
    1.25
    >>>>>>
    1.14
    >>>>>>>>
    1.01
    <<<
    0.96
    >>>>>>>
    0.89
     <<<
    0.79
    <<<<
    0.65
    Act Density 0.014%

    No Known Activations