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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reun
    -0.07
     причин
    -0.06
     Quar
    -0.06
    -console
    -0.06
    ','#
    -0.06
     českých
    -0.06
     Anth
    -0.06
     dose
    -0.06
    .correct
    -0.06
     August
    -0.06
    POSITIVE LOGITS
    rr
    0.07
    rahim
    0.07
     قن
    0.06
    Favorite
    0.06
    ijd
    0.06
    [child
    0.06
    .Builder
    0.06
    Last
    0.06
    oring
    0.06
    ир
    0.06
    Act Density 0.000%

    No Known Activations