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

    Neuronpedia

    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _utils
    -0.07
    -ब
    -0.07
    省
    -0.06
    Dynamic
    -0.06
     Kadın
    -0.06
    Turn
    -0.06
    ornado
    -0.06
     省
    -0.06
    .mock
    -0.06
    omu
    -0.06
    POSITIVE LOGITS
    -Disposition
    0.07
    license
    0.06
    onent
    0.06
    /Instruction
    0.06
     Rendering
    0.06
     commencement
    0.06
     придется
    0.06
     dismissal
    0.06
     hepsi
    0.06
    하지만
    0.06
    Act Density 0.058%

    No Known Activations