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

    Neuronpedia

    INDEX
    Explanations

    Destruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    बाट
    -0.08
    ब
    -0.08
     खर्च
    -0.08
     Obrig
    -0.08
     enthusiastic
    -0.08
    र्प
    -0.08
     क्लब
    -0.08
    ♂
    -0.07
     Barbara
    -0.07
    arden
    -0.07
    POSITIVE LOGITS
     rumored
    0.09
     fake
    0.09
    fake
    0.08
     breakthroughs
    0.08
     inexist
    0.08
    vier
    0.08
     imaginary
    0.08
     breakthrough
    0.07
    _fake
    0.07
    Fake
    0.07
    Act Density 0.001%

    No Known Activations