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

    Neuronpedia

    INDEX
    Explanations

    Alaska

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ystate
    -0.07
    Paint
    -0.06
     endured
    -0.06
    фик
    -0.06
    >d
    -0.06
    ังก
    -0.06
    血
    -0.06
    .%
    -0.06
    สง
    -0.06
    POSITIVE LOGITS
    십
    0.07
     unrest
    0.07
     KD
    0.07
     sexism
    0.07
    bestos
    0.06
     canadian
    0.06
    .bind
    0.06
     telah
    0.06
    肯
    0.06
    -looking
    0.06
    Act Density 0.000%

    No Known Activations