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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ст
    -0.07
     пр
    -0.06
    setChecked
    -0.06
    accent
    -0.06
     mně
    -0.06
    passwd
    -0.06
    ่ะ
    -0.06
    ，這
    -0.06
    شته
    -0.06
     Мет
    -0.06
    POSITIVE LOGITS
    霊
    0.06
    优
    0.06
    miyor
    0.06
    !!!!
    0.06
    erdale
    0.06
    _claim
    0.06
    _class
    0.06
    �
    0.06
    oğlu
    0.06
    ami
    0.06
    Act Density 0.001%

    No Known Activations