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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坤
    -0.07
     Williamson
    -0.07
    ﺯ
    -0.06
    -program
    -0.06
    enced
    -0.06
    .He
    -0.06
    onenumber
    -0.06
     umoż
    -0.06
    (nr
    -0.06
     Compliance
    -0.06
    POSITIVE LOGITS
     casos
    0.07
    iciel
    0.07
     �
    0.07
     intéress
    0.07
    אמא
    0.07
     Tata
    0.07
    Date
    0.06
    unteer
    0.06
     AL
    0.06
    Sub
    0.06
    Act Density 0.020%

    No Known Activations