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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cla
    -0.07
    hashCode
    -0.07
     الخامسة
    -0.07
     handwritten
    -0.06
     naughty
    -0.06
    )const
    -0.06
     کارگرد
    -0.06
    ALTH
    -0.06
    _music
    -0.06
     nền
    -0.06
    POSITIVE LOGITS
     servo
    0.06
     sidew
    0.06
    lacağ
    0.06
     와
    0.06
    and
    0.06
    eded
    0.06
    iated
    0.06
    lında
    0.06
    グ
    0.06
    ılacak
    0.06
    Act Density 0.087%

    No Known Activations