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

    Neuronpedia

    INDEX
    Explanations

    genuinely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ☍
    -0.07
     kính
    -0.07
     perish
    -0.07
    ')}}"></
    -0.07
     anonymous
    -0.07
     UnsupportedOperationException
    -0.07
     loved
    -0.07
     gastro
    -0.06
     ribs
    -0.06
    */}↵
    -0.06
    POSITIVE LOGITS
    scape
    0.07
    有效性
    0.07
    米兰
    0.07
    сад
    0.07
     switched
    0.07
     ballots
    0.07
     signs
    0.07
    ge
    0.06
    ؼ
    0.06
    ificado
    0.06
    Act Density 0.073%

    No Known Activations