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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     úřad
    -0.06
    nicos
    -0.06
    梁
    -0.06
     conting
    -0.06
     ارزی
    -0.06
     pass
    -0.06
    tep
    -0.06
    see
    -0.06
    "-
    -0.06
    érieur
    -0.06
    POSITIVE LOGITS
    _LOG
    0.07
     Polish
    0.07
     nb
    0.07
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.07
     الرياض
    0.06
     コ
    0.06
     Nebraska
    0.06
    Register
    0.06
     lovely
    0.06
    _SIGNAL
    0.06
    Act Density 0.000%

    No Known Activations