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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rendition
    -0.09
    استقلال
    -0.07
     cmap
    -0.07
    皛
    -0.07
     Mister
    -0.07
    odcast
    -0.07
    mówi
    -0.07
    䴓
    -0.07
    ワイン
    -0.07
    抑郁症
    -0.07
    POSITIVE LOGITS
    淺
    0.08
    ượng
    0.07
    簡單
    0.07
    쭤
    0.07
     substantial
    0.07
    يك
    0.07
    ос
    0.07
     SOME
    0.07
    驹
    0.07
    *N
    0.06
    Act Density 0.026%

    No Known Activations