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

    Neuronpedia

    INDEX
    Explanations

    concentrating power, depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஷி
    0.51
    ]。
    0.51
    ீர்கள்
    0.48
     minutos
    0.48
     erw
    0.47
     \%$.
    0.47
     dakika
    0.46
    ढ़ाई
    0.46
     giocando
    0.46
    ඍ
    0.46
    POSITIVE LOGITS
    b
    0.48
    ob
    0.46
    tyn
    0.46
    ̃
    0.46
    onal
    0.45
    ue
    0.44
    ap
    0.44
    rov
    0.44
    ilateral
    0.44
    ov
    0.43
    Act Density 0.000%

    No Known Activations