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

    Neuronpedia

    INDEX
    Explanations

    programming tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ゛
    0.70
    anger
    0.70
     Sart
    0.67
    ANGER
    0.65
    rometer
    0.64
    launcher
    0.63
    দাতা
    0.63
    appointments
    0.63
     व्यास
    0.62
    comp
    0.62
    POSITIVE LOGITS
    ㄖ
    0.76
    чен
    0.76
     Chinese
    0.74
    NAL
    0.74
    笹
    0.74
     inmate
    0.73
     Rohingya
    0.73
    NELL
    0.71
     TikTok
    0.71
    тельному
    0.69
    Act Density 0.001%

    No Known Activations