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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᥒ
    -0.08
    𝕖
    -0.07
     Mp
    -0.07
    能源
    -0.07
    😤
    -0.07
     explain
    -0.07
     Canyon
    -0.07
    閱讀
    -0.07
    accion
    -0.07
     commentator
    -0.07
    POSITIVE LOGITS
     Phạm
    0.08
     Wy
    0.07
     почти
    0.07
     cầm
    0.06
    .UseVisualStyleBackColor
    0.06
    هائي
    0.06
     Wrapper
    0.06
    非常适合
    0.06
    凡
    0.06
     Geme
    0.06
    Act Density 0.001%

    No Known Activations