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

    Neuronpedia

    INDEX
    Explanations

    Car development and racing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    在外
    -0.07
     luego
    -0.07
     שא
    -0.07
    創造
    -0.06
    ТЬ
    -0.06
     wer
    -0.06
    .O
    -0.06
    出来
    -0.06
     Basic
    -0.06
    一颗
    -0.06
    POSITIVE LOGITS
     Specs
    0.08
    社会发展
    0.08
    㬊
    0.07
    jualan
    0.07
    severity
    0.07
    ☔
    0.07
     SWT
    0.07
    _Size
    0.07
    .rectangle
    0.07
    (answer
    0.07
    Act Density 0.014%

    No Known Activations