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

    Neuronpedia

    INDEX
    Explanations

    assignments and equality statements in code

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

    true or false values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.48
    MessageOf
    -0.48
    ----</
    -0.47
    OrNil
    -0.46
     ProtoMessage
    -0.45
    rungsseite
    -0.43
    Selfer
    -0.41
    TargetException
    -0.40
     ब्रेकडाउन
    -0.40
     jspb
    -0.39
    POSITIVE LOGITS
     false
    0.90
     true
    0.73
    false
    0.72
     False
    0.69
    true
    0.64
    False
    0.64
     FALSE
    0.62
     True
    0.59
     verdadeiro
    0.55
     TRUE
    0.55
    Act Density 0.004%

    No Known Activations