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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horizon
    -0.08
    "?
    -0.07
     Cast
    -0.07
    _NR
    -0.06
    _seek
    -0.06
     yelling
    -0.06
    '?
    -0.06
    -shift
    -0.06
    τή
    -0.06
    ん
    -0.06
    POSITIVE LOGITS
     buttonText
    0.07
     ++)
    0.06
    んど
    0.06
    =image
    0.06
     nhắc
    0.06
     threesome
    0.06
     correctamente
    0.06
     Pey
    0.06
     errone
    0.06
    .getItems
    0.06
    Act Density 0.001%

    No Known Activations