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

    Neuronpedia

    INDEX
    Explanations

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    scribed
    -0.07
    .Size
    -0.07
     maple
    -0.06
     discrimination
    -0.06
     ripple
    -0.06
    334
    -0.06
     Parsing
    -0.06
    >
    -0.06
     computation
    -0.06
     Bosch
    -0.06
    POSITIVE LOGITS
     تازه
    0.07
    ामन
    0.07
     خطر
    0.07
    dyn
    0.07
    ๊ก
    0.06
    �
    0.06
     kosher
    0.06
    _rng
    0.06
     بدن
    0.06
    사업
    0.06
    Act Density 0.000%

    No Known Activations