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

    Neuronpedia

    INDEX
    Explanations

    -handed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kunnen
    -0.06
     persona
    -0.06
    ecera
    -0.06
    637
    -0.06
    �
    -0.06
     سب
    -0.06
    xEB
    -0.06
     vi
    -0.06
    -0.06
    :\/\/
    -0.06
    POSITIVE LOGITS
     warfare
    0.07
     feeder
    0.07
     carnival
    0.07
    ural
    0.07
    minus
    0.07
     sellers
    0.07
    ilmington
    0.06
    _ONCE
    0.06
    .Translate
    0.06
     dancing
    0.06
    Act Density 0.017%

    No Known Activations