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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kir
    -0.08
     Iraq
    -0.08
    _fill
    -0.08
     hurts
    -0.08
     fillers
    -0.08
     Mauritius
    -0.07
     Fri
    -0.07
    itura
    -0.07
     Fill
    -0.07
    shëm
    -0.07
    POSITIVE LOGITS
    正确
    0.09
    有所
    0.09
     efficacement
    0.09
     effectively
    0.09
     effectiveness
    0.09
    安心
    0.08
    充分
    0.08
    事情
    0.08
     эффективно
    0.08
     разобраться
    0.08
    Act Density 0.059%

    No Known Activations