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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
              
↵
    -0.07
     ввод
    -0.07
    itura
    -0.07
     риз
    -0.07
     правила
    -0.06
    十分
    -0.06
     Ř
    -0.06
     б
    -0.06
    出版
    -0.06
    Hits
    -0.06
    POSITIVE LOGITS
     bodily
    0.07
    aged
    0.06
     hyp
    0.06
     illegal
    0.06
    ”;
    0.06
     gon
    0.06
     Burma
    0.06
    (eq
    0.06
     Cur
    0.06
     eyebrow
    0.06
    Act Density 0.000%

    No Known Activations