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

    Neuronpedia

    INDEX
    Explanations

    introducing an explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তৃণমূল
    0.64
    於是
    0.63
     отсутствии
    0.63
    atch
    0.62
     ว่า
    0.61
     이때
    0.60
    ValMap
    0.60
     aquí
    0.60
     ਨਹੀਂ
    0.59
    堊
    0.59
    POSITIVE LOGITS
    Discussion
    0.76
    ppe
    0.73
    Compare
    0.70
    compared
    0.69
    胡
    0.67
     Compare
    0.66
    iani
    0.66
    PRE
    0.66
     Compared
    0.65
    Discuss
    0.65
    Act Density 0.168%

    No Known Activations