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

    Neuronpedia

    INDEX
    Explanations

    references to written content or communication indicators, such as messages and signs

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

    labeled "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.63
    skjaer
    -0.48
     recueil
    -0.47
    TypedDataSet
    -0.47
     protoimpl
    -0.43
    aarrggbb
    -0.43
    клопе
    -0.42
    httphttps
    -0.42
     Vorbild
    -0.42
    itespace
    -0.41
    POSITIVE LOGITS
     labeled
    0.40
     lettered
    0.39
    ceği
    0.39
     hiệu
    0.38
    endswith
    0.36
    alang
    0.36
     umož
    0.36
    potential
    0.36
    typeDefinition
    0.36
    ceğini
    0.35
    Act Density 0.041%

    No Known Activations