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

    Neuronpedia

    INDEX
    Explanations

    job application answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    striatis
    0.50
     स्टूडेंट
    0.50
    小說
    0.46
     శ
    0.46
     직
    0.46
    rimination
    0.46
    žev
    0.46
     ስ
    0.46
    圖像
    0.46
     파
    0.45
    POSITIVE LOGITS
    ря
    0.43
     ^=
    0.43
     kẻ
    0.42
    dDays
    0.42
     nghịch
    0.42
    lun
    0.42
    (^^
    0.42
    ’’
    0.41
     vui
    0.41
    以便
    0.41
    Act Density 0.001%

    No Known Activations