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

    Neuronpedia

    INDEX
    Explanations

    selected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affirmation
    -0.09
     قصة
    -0.07
    資金
    -0.07
    确保
    -0.07
    勖
    -0.07
    㐱
    -0.07
    רם
    -0.07
    landı
    -0.07
     displaced
    -0.07
    ﰴ
    -0.06
    POSITIVE LOGITS
     takeaway
    0.07
    %%↵
    0.07
    (dead
    0.07
    道路交通
    0.07
     bbw
    0.07
    Readable
    0.07
    Take
    0.07
    Updates
    0.07
    嚴
    0.07
     bufio
    0.07
    Act Density 0.014%

    No Known Activations