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

    Neuronpedia

    INDEX
    Explanations

    communication and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.99
     türlü
    0.98
    िक
    0.97
     få
    0.97
    ్‌
    0.95
    ança
    0.94
    وأ
    0.94
    ető
    0.94
     geliyor
    0.94
    𝗳
    0.93
    POSITIVE LOGITS
     зав
    0.93
    いずれ
    0.89
    かかる
    0.81
    tras
    0.80
    牲
    0.80
    comm
    0.78
    PLAY
    0.77
    ੍ਹ
    0.75
     Shuang
    0.75
    шно
    0.74
    Act Density 0.003%

    No Known Activations