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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     전화
    -0.06
    urr
    -0.06
    ajas
    -0.06
     Prairie
    -0.06
    ipe
    -0.06
    在线观看
    -0.06
     TResult
    -0.06
     Hydra
    -0.06
     flames
    -0.06
     nursing
    -0.06
    POSITIVE LOGITS
     rely
    0.08
    aise
    0.07
    assertFalse
    0.07
    ////////////////////////////////////////////////////////
    0.07
    FieldName
    0.07
    0.07
     stě
    0.06
    .'"
    0.06
     ऐस
    0.06
     bytecode
    0.06
    Act Density 0.002%

    No Known Activations