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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    app
    -0.07
     Francisco
    -0.06
    apo
    -0.06
     Shelf
    -0.06
    importe
    -0.06
    раб
    -0.06
    �
    -0.06
    Https
    -0.06
     toplumsal
    -0.06
    .descriptor
    -0.06
    POSITIVE LOGITS
    DATA
    0.06
    BeNull
    0.06
    _ALT
    0.06
    几乎
    0.06
    emploi
    0.06
     Sue
    0.06
     "↵
    0.06
     Mutation
    0.06
    eshire
    0.06
     relieved
    0.05
    Act Density 0.012%

    No Known Activations