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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?',
    -0.06
    ]=-
    -0.06
     relationship
    -0.06
    成为
    -0.06
    Currency
    -0.06
     Weird
    -0.06
     cautious
    -0.06
     Criminal
    -0.06
    Minor
    -0.06
    سازی
    -0.06
    POSITIVE LOGITS
    using
    0.07
     मल
    0.07
     žal
    0.07
     getModel
    0.06
    .unshift
    0.06
     creo
    0.06
    .RE
    0.06
    �
    0.06
    _Height
    0.06
     HMS
    0.06
    Act Density 0.006%

    No Known Activations