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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zug
    -0.07
     analytical
    -0.07
    morph
    -0.07
     anarchists
    -0.07
    ☟
    -0.07
    Service
    -0.06
    _J
    -0.06
    _Invoke
    -0.06
    发展格局
    -0.06
     course
    -0.06
    POSITIVE LOGITS
     Ster
    0.07
     Millionen
    0.06
     elseif
    0.06
    !(
    0.06
    íd
    0.06
     الأمير
    0.06
     Intelli
    0.06
    %
    0.06
    illion
    0.06
     immortal
    0.06
    Act Density 0.126%

    No Known Activations