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

    Neuronpedia

    INDEX
    Explanations

    hobbies and activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Func
    -0.07
    Colorado
    -0.07
     Indigenous
    -0.07
    Mode
    -0.07
    ути
    -0.07
     상대
    -0.06
    就是
    -0.06
    confidence
    -0.06
    ΙΝ
    -0.06
    олов
    -0.06
    POSITIVE LOGITS
    cdot
    0.06
    -proxy
    0.06
     дер
    0.06
    utr
    0.06
     قاب
    0.06
     schwar
    0.06
    ังส
    0.06
    -Петерб
    0.05
    าคาร
    0.05
    _km
    0.05
    Act Density 0.077%

    No Known Activations