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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    佑
    -0.06
     drew
    -0.06
     pdata
    -0.06
    规模
    -0.06
    鲁
    -0.06
    acky
    -0.06
     lookahead
    -0.06
    look
    -0.06
    .Here
    -0.06
    sty
    -0.06
    POSITIVE LOGITS
    książka
    0.08
    stdlib
    0.07
     ağ
    0.07
    /game
    0.07
     canine
    0.07
    毪
    0.07
     UDP
    0.07
    .Bind
    0.07
     quant
    0.07
    🧙
    0.07
    Act Density 0.005%

    No Known Activations