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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᠦ
    -0.08
    ẩm
    -0.07
    xca
    -0.07
    �
    -0.07
    𝚆
    -0.06
     לעית
    -0.06
     FileInputStream
    -0.06
     umożliw
    -0.06
    การแสดง
    -0.06
    ʧ
    -0.06
    POSITIVE LOGITS
     leak
    0.08
    -person
    0.07
    ifacts
    0.07
    buffer
    0.07
    ске
    0.07
     universe
    0.07
    _account
    0.07
    syntax
    0.07
    價格
    0.07
    (Y
    0.07
    Act Density 0.003%

    No Known Activations