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

    Neuronpedia

    INDEX
    Explanations

    official/unofficial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Connectivity
    -0.07
    发展
    -0.06
    ymax
    -0.06
     completely
    -0.06
     Appl
    -0.06
    595
    -0.06
     nes
    -0.06
     persuade
    -0.06
     эффек
    -0.06
     mushrooms
    -0.06
    POSITIVE LOGITS
     unofficial
    0.13
     unfair
    0.07
     amt
    0.07
    official
    0.06
    lower
    0.06
    เป
    0.06
     Schwar
    0.06
    ична
    0.06
    _theta
    0.06
    edith
    0.06
    Act Density 0.005%

    No Known Activations