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

    Neuronpedia

    INDEX
    Explanations

    later

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一头
    -0.07
    uforia
    -0.07
     cryptography
    -0.07
    __);↵
    -0.07
    Buff
    -0.07
     fos
    -0.07
    引发
    -0.06
     Fab
    -0.06
    Ậ
    -0.06
    .INFO
    -0.06
    POSITIVE LOGITS
    ものは
    0.08
     grandson
    0.07
    Registry
    0.07
    Playable
    0.07
     EX
    0.07
    ridge
    0.07
    회의
    0.07
     classroom
    0.07
    栽
    0.07
     Reservation
    0.06
    Act Density 0.037%

    No Known Activations