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

    Neuronpedia

    INDEX
    Explanations

    stem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    warf
    -0.07
    川
    -0.07
     welt
    -0.07
     mode
    -0.07
    906
    -0.06
    ₃
    -0.06
     bao
    -0.06
    'na
    -0.06
    .words
    -0.06
     taxes
    -0.06
    POSITIVE LOGITS
     fence
    0.07
    .us
    0.06
    secure
    0.06
    گاهی
    0.06
     skepticism
    0.06
    (MethodImplOptions
    0.06
     audits
    0.06
    υ
    0.05
    adil
    0.05
     insanlar
    0.05
    Act Density 0.008%

    No Known Activations