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

    Neuronpedia

    INDEX
    Explanations

    Stat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =d
    -0.07
    意味
    -0.07
    _BC
    -0.07
    =c
    -0.07
    (J
    -0.07
    Ltd
    -0.07
     cv
    -0.07
     tương
    -0.07
    >C
    -0.07
     verz
    -0.07
    POSITIVE LOGITS
    储存
    0.07
    _refs
    0.06
    enkins
    0.06
    מטה
    0.06
     Fra
    0.06
    regist
    0.06
    że
    0.06
    ethyst
    0.06
    _FROM
    0.06
    課程
    0.06
    Act Density 0.001%

    No Known Activations