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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    準
    -0.07
    uellen
    -0.07
     occupy
    -0.07
    em
    -0.06
    Ex
    -0.06
     antennas
    -0.06
     propulsion
    -0.06
    _CHILD
    -0.06
    릭
    -0.06
    'il
    -0.06
    POSITIVE LOGITS
     Gors
    0.08
    awesome
    0.06
     Sisters
    0.06
    พย
    0.06
    руется
    0.06
    _ONLY
    0.06
    γραφ
    0.06
     billions
    0.06
    أت
    0.06
    (typeof
    0.06
    Act Density 0.005%

    No Known Activations