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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disadvantage
    -0.07
    _dicts
    -0.07
     computational
    -0.07
     dividend
    -0.06
    itelist
    -0.06
     freedoms
    -0.06
     embeddings
    -0.06
    Pause
    -0.06
     لم
    -0.06
    心理
    -0.06
    POSITIVE LOGITS
     могут
    0.07
    ()[
    0.06
     Sophie
    0.06
    617
    0.06
    980
    0.06
     Aircraft
    0.06
    .entities
    0.06
     dgv
    0.06
     Bengals
    0.06
    (exp
    0.06
    Act Density 0.012%

    No Known Activations