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

    Neuronpedia

    INDEX
    Explanations

    a mix of code snippets and possible french language

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izr
    -0.60
    SourceChecksum
    -0.59
    NewGuid
    -0.58
    lusconi
    -0.50
    WriteAttribute
    -0.49
    Биография
    -0.48
    Madonna
    -0.44
     Madonna
    -0.43
    ies
    -0.43
    TargetException
    -0.41
    POSITIVE LOGITS
    Personensuche
    0.95
     réfugi
    0.76
     voren
    0.71
     vPvB
    0.67
     originaire
    0.67
     précédents
    0.67
    Parcelize
    0.67
     littéraire
    0.65
    rentices
    0.65
    twimg
    0.64
    Act Density 0.643%

    No Known Activations