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

    Neuronpedia

    INDEX
    Explanations

    parties and guests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    자
    -0.07
    英国
    -0.07
    围
    -0.07
     young
    -0.07
    俞
    -0.06
     undert
    -0.06
    Aug
    -0.06
     쉽
    -0.06
    脱离
    -0.06
    ette
    -0.06
    POSITIVE LOGITS
     Dedicated
    0.08
     рад
    0.07
    )،
    0.07
    Propagation
    0.07
     ingen
    0.07
     Categories
    0.07
     fab
    0.06
    仙境
    0.06
    keley
    0.06
     SSH
    0.06
    Act Density 0.157%

    No Known Activations