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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้าหน
    -0.07
    :utf
    -0.06
    -times
    -0.06
    ัณฑ
    -0.06
    สด
    -0.06
     blocks
    -0.06
     distributed
    -0.06
    _clusters
    -0.06
    리그
    -0.06
    _documento
    -0.06
    POSITIVE LOGITS
    .mixer
    0.07
    grav
    0.06
    خصوص
    0.06
     건강
    0.06
     eser
    0.06
     Hutchinson
    0.06
    eptal
    0.06
     nir
    0.06
    RESSION
    0.06
    aze
    0.06
    Act Density 0.001%

    No Known Activations