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

    Neuronpedia

    INDEX
    Explanations

    say numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cnn
    -0.07
     Laguna
    -0.07
    'Connor
    -0.07
    STATIC
    -0.07
     spinach
    -0.07
    ódigo
    -0.07
    Cómo
    -0.07
     Scheduler
    -0.07
    Jos
    -0.07
     IMAGE
    -0.07
    POSITIVE LOGITS
     day
    0.07
     symbol
    0.07
    _
    0.07
    煃
    0.07
    其余
    0.07
    ═
    0.07
    ие
    0.07
    .AutoScale
    0.07
     making
    0.06
    ימ
    0.06
    Act Density 0.006%

    No Known Activations