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

    Neuronpedia

    INDEX
    Explanations

    革命

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    락
    -0.08
    (Size
    -0.08
     fryer
    -0.07
    నున్న
    -0.07
     Forte
    -0.07
     refres
    -0.07
     أس
    -0.07
    ianz
    -0.07
    фера
    -0.07
    ంగా
    -0.07
    POSITIVE LOGITS
     vigilance
    0.08
     spirit
    0.08
     historias
    0.08
     undertaken
    0.08
     historia
    0.07
     kad
    0.07
    事业
    0.07
    壮
    0.07
     sırasında
    0.07
     جاري
    0.07
    Act Density 0.010%

    No Known Activations