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

    Neuronpedia

    INDEX
    Explanations

    mode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    䓖
    -0.07
    各家
    -0.07
    anging
    -0.07
    너
    -0.07
     rowIndex
    -0.07
    高价
    -0.07
    __↵
    -0.07
     znalazł
    -0.07
    往往是
    -0.06
     Neue
    -0.06
    POSITIVE LOGITS
     mode
    0.09
     Cin
    0.08
    锭
    0.07
     출력
    0.07
    obe
    0.07
     OUTPUT
    0.07
     Camera
    0.07
     רי
    0.07
     Ми
    0.07
    	default
    0.07
    Act Density 0.018%

    No Known Activations