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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dll
    -0.07
    Touch
    -0.06
     manned
    -0.06
    .strict
    -0.06
     �
    -0.06
    	pstmt
    -0.06
     дом
    -0.06
    pth
    -0.06
    -D
    -0.06
    彻
    -0.06
    POSITIVE LOGITS
    VertexUvs
    0.06
    μιουργ
    0.06
    .Auto
    0.06
    Mismatch
    0.06
    _CANNOT
    0.06
     Offensive
    0.06
    ffects
    0.06
    �
    0.06
    .Nome
    0.06
    (first
    0.06
    Act Density 0.005%

    No Known Activations