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

    Neuronpedia

    INDEX
    Explanations

    Durations of time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    worker
    -0.07
    hole
    -0.06
    machine
    -0.06
     pathological
    -0.06
    _OVERRIDE
    -0.06
    _source
    -0.06
    _canvas
    -0.06
     towns
    -0.06
    chen
    -0.06
    band
    -0.06
    POSITIVE LOGITS
     disclosing
    0.07
     <<↵
    0.07
    .Offset
    0.06
     カ
    0.06
     kp
    0.06
    _sibling
    0.06
     동일
    0.06
    dbl
    0.06
     शर
    0.06
     Tet
    0.06
    Act Density 0.025%

    No Known Activations