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

    Neuronpedia

    INDEX
    Explanations

    gone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dfunding
    -0.09
     colour
    -0.06
    ськими
    -0.06
     WHERE
    -0.06
     rubber
    -0.06
    .setStyle
    -0.06
     ")↵
    -0.06
    -quality
    -0.06
    .readLine
    -0.06
    ('.
    -0.06
    POSITIVE LOGITS
     gone
    0.10
     Gone
    0.09
    ylan
    0.07
    gone
    0.07
    ему
    0.07
    rahim
    0.07
    πον
    0.06
     Antar
    0.06
    ıs
    0.06
    antd
    0.06
    Act Density 0.004%

    No Known Activations