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

    Neuronpedia

    INDEX
    Explanations

    code or equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    浦
    -0.07
     Evalu
    -0.07
    언
    -0.07
     czy
    -0.07
    属
    -0.06
    경제
    -0.06
    _Last
    -0.06
    _DECLARE
    -0.06
    排序
    -0.06
    atives
    -0.06
    POSITIVE LOGITS
    .gb
    0.06
    .getValue
    0.06
    (Action
    0.06
    <AM
    0.06
    <Movie
    0.06
     sexism
    0.06
    radouro
    0.06
     assassination
    0.06
     recommendation
    0.06
     factions
    0.06
    Act Density 0.000%

    No Known Activations