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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -stat
    -0.07
    _texts
    -0.07
    ",↵↵
    -0.06
    Aux
    -0.06
     مه
    -0.06
    ई
    -0.06
     crist
    -0.06
    pcm
    -0.06
    >"
↵
    -0.06
    Io
    -0.06
    POSITIVE LOGITS
    osloven
    0.07
     も
    0.07
     Res
    0.07
     wen
    0.06
     Continent
    0.06
     necessary
    0.06
     第三
    0.06
    _User
    0.06
     også
    0.06
    lf
    0.06
    Act Density 0.003%

    No Known Activations