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

    Neuronpedia

    INDEX
    Explanations

    scientific paper introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Registrar
    -0.07
    PhoneNumber
    -0.06
    토
    -0.06
    )))
    -0.06
     misses
    -0.06
    conda
    -0.06
    ẵ
    -0.06
    �
    -0.06
     convenience
    -0.06
    廠
    -0.06
    POSITIVE LOGITS
    イズ
    0.07
    (topic
    0.07
    vp
    0.07
    ?",
    0.06
    VP
    0.06
     ι
    0.06
     Fen
    0.06
    (j
    0.06
    (GL
    0.06
     라이
    0.06
    Act Density 0.005%

    No Known Activations