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

    Neuronpedia

    INDEX
    Explanations

    instances of regex patterns and escape sequences

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

    Character after backslash

    np_acts-logits-general · gemini-2.0-flash

    regular expression escape sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.67
     defaultstate
    -0.63
    principalTable
    -0.63
     ")");
    -0.62
    enumi
    -0.62
    enumii
    -0.60
    CopyWith
    -0.59
    Cubit
    -0.58
    %");
    -0.58
    %")
    -0.56
    POSITIVE LOGITS
     vPvB
    0.63
    AsStream
    0.51
     pair
    0.49
     w
    0.49
     Baru
    0.49
    aronne
    0.48
    osph
    0.48
    ouge
    0.47
    /**
    0.47
    ocument
    0.47
    Act Density 0.206%

    No Known Activations