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

    Neuronpedia

    INDEX
    Explanations

    chemical symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inn
    -0.07
    _p
    -0.07
     latina
    -0.07
    .LoadScene
    -0.06
    琳
    -0.06
     Michel
    -0.06
    ᘑ
    -0.06
    𝙖
    -0.06
    ｡
    -0.06
    🍙
    -0.06
    POSITIVE LOGITS
    ﺶ
    0.07
    Չ
    0.07
    ехал
    0.07
    יות
    0.06
    챵
    0.06
    一轮
    0.06
    一夜
    0.06
    鸷
    0.06
     centrif
    0.06
     Arithmetic
    0.06
    Act Density 0.015%

    No Known Activations