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

    Neuronpedia

    INDEX
    Explanations

    and/or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    안
    -0.06
    一点
    -0.06
     tắt
    -0.06
     BEFORE
    -0.06
    HAS
    -0.06
     conscience
    -0.06
    ison
    -0.06
     AD
    -0.06
     uncertainties
    -0.06
    que
    -0.06
    POSITIVE LOGITS
    	iter
    0.07
     lief
    0.07
    _U
    0.07
     vede
    0.06
    =u
    0.06
    TOT
    0.06
     modne
    0.06
    ород
    0.06
     oe
    0.06
    人类
    0.06
    Act Density 0.022%

    No Known Activations