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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    regnum
    -0.07
     captivity
    -0.07
     Kang
    -0.07
    =True
    -0.06
    'es
    -0.06
    acy
    -0.06
    轉
    -0.06
    _note
    -0.06
     wish
    -0.06
     spin
    -0.06
    POSITIVE LOGITS
    --------------------------------------------------------------------------↵
    0.06
     Вели
    0.06
     ули
    0.06
     staunch
    0.06
     xong
    0.06
    LowerCase
    0.06
     equality
    0.06
    ΕΛ
    0.06
    的情
    0.06
     Kirst
    0.06
    Act Density 0.019%

    No Known Activations