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

    Neuronpedia

    INDEX
    Explanations

    percentage increase/decrease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -supported
    -0.08
     vap
    -0.08
    Evidence
    -0.08
    vidence
    -0.07
    Supported
    -0.07
    Realm
    -0.07
     retired
    -0.07
     trio
    -0.07
    icions
    -0.07
     보
    -0.07
    POSITIVE LOGITS
     mengalami
    0.09
     nouve
    0.09
    loch
    0.09
     Herkunft
    0.09
     sanhi
    0.08
    തമ
    0.08
     numerator
    0.08
    leriniň
    0.08
    umbuhan
    0.08
     difference
    0.08
    Act Density 0.025%

    No Known Activations