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

    Neuronpedia

    INDEX
    Explanations

    uced/induced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    밧
    -0.07
    oline
    -0.07
    灯火
    -0.07
    ار
    -0.07
    黑夜
    -0.07
    ,)
    -0.07
    otte
    -0.07
    違う
    -0.07
     boldly
    -0.07
     Matt
    -0.07
    POSITIVE LOGITS
     plugin
    0.08
    子ど
    0.08
    เง
    0.08
    .where
    0.07
     induce
    0.07
     lexer
    0.07
    留学生
    0.07
    小学生
    0.07
     induces
    0.07
    煁
    0.07
    Act Density 0.030%

    No Known Activations