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

    Neuronpedia

    INDEX
    Explanations

    Chromium project URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atty
    -0.08
    ński
    -0.08
    ,type
    -0.07
    Master
    -0.07
     -↵↵
    -0.07
    escape
    -0.07
    撮
    -0.07
     scri
    -0.07
     jokes
    -0.07
    返回搜狐
    -0.06
    POSITIVE LOGITS
    ер
    0.08
    宕
    0.08
     inout
    0.07
    胚
    0.07
    商
    0.07
     manera
    0.07
     SIGNAL
    0.07
     companion
    0.07
     Payload
    0.07
     بدون
    0.07
    Act Density 0.001%

    No Known Activations