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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     붙
    -0.06
     هم
    -0.06
     admin
    -0.06
     Special
    -0.06
    (album
    -0.06
    cur
    -0.06
    _SO
    -0.06
    ادي
    -0.06
     Ventures
    -0.06
     Mirror
    -0.06
    POSITIVE LOGITS
    Inf
    0.07
    This
    0.07
     Ethiopian
    0.06
    venience
    0.06
    га
    0.06
    _traits
    0.06
    mus
    0.06
    LANGUAGE
    0.06
     حسین
    0.06
     locom
    0.06
    Act Density 0.004%

    No Known Activations