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

    Neuronpedia

    INDEX
    Explanations

    music album performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    面對
    -0.07
    <![
    -0.06
    如
    -0.06
     Эт
    -0.06
     erotisch
    -0.06
    emed
    -0.06
     confessed
    -0.06
     �
    -0.06
    部分
    -0.06
    胃
    -0.06
    POSITIVE LOGITS
     filtr
    0.08
     Singer
    0.07
    .getSession
    0.07
    람
    0.07
    上涨
    0.07
    诠释
    0.07
     Werner
    0.07
     unic
    0.07
    finance
    0.07
     Bor
    0.07
    Act Density 0.043%

    No Known Activations