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

    Neuronpedia

    INDEX
    Explanations

    Code and data formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timid
    -0.07
     adher
    -0.07
     hammer
    -0.07
    acción
    -0.07
     Cristiano
    -0.06
    วร
    -0.06
    dehyde
    -0.06
     Jupiter
    -0.06
    <TResult
    -0.06
     Entre
    -0.06
    POSITIVE LOGITS
     기준
    0.07
    ellt
    0.07
     Ci
    0.07
    (da
    0.06
     bliss
    0.06
    argin
    0.06
     cinemat
    0.06
    .Misc
    0.06
    ....
    0.06
    =="
    0.06
    Act Density 0.002%

    No Known Activations