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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters and syntax patterns

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

    PHP code and shell variables

    np_acts-logits-general · gemini-2.0-flash

    code, "$", "deaths"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.75
    UserScript
    -0.72
    UnsafeEnabled
    -0.71
    LookAnd
    -0.69
     """
    -0.62
    SequentialGroup
    -0.62
    saraba
    -0.58
     án
    -0.57
     Signalez
    -0.57
     <.
    -0.57
    POSITIVE LOGITS
    $
    1.57
     $
    0.97
    foreach
    0.94
    ($
    0.87
    //$
    0.86
    [$
    0.83
    @$
    0.75
    $_
    0.74
    if
    0.74
    #$
    0.73
    Act Density 0.035%

    No Known Activations