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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、高
    -0.09
     residences
    -0.08
    remarks
    -0.08
    zeichnung
    -0.08
    Evt
    -0.08
    алл
    -0.08
     서비스
    -0.08
     bother
    -0.08
     ورد
    -0.08
    _service
    -0.08
    POSITIVE LOGITS
     (((
    0.08
    xor
    0.08
     xor
    0.08
    IMP
    0.08
     Ausgang
    0.08
     получится
    0.08
     komb
    0.08
     комбина
    0.08
     получилось
    0.08
     klasik
    0.07
    Act Density 0.015%

    No Known Activations