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

    Neuronpedia

    INDEX
    Explanations

    ":

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eres
    -0.07
    eeper
    -0.07
    ishing
    -0.07
     Keller
    -0.07
    -te
    -0.06
    -os
    -0.06
    лик
    -0.06
    chosen
    -0.06
    ilter
    -0.06
     Remark
    -0.06
    POSITIVE LOGITS
     kazanç
    0.06
    昌
    0.06
     ší
    0.06
     comentario
    0.06
     생
    0.06
    hea
    0.06
     आज
    0.06
     이해
    0.06
    (Room
    0.06
     centerX
    0.06
    Act Density 0.013%

    No Known Activations