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

    Neuronpedia

    INDEX
    Explanations

    mortality, repetition, or specific sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    0.56
    ня
    0.49
    فون
    0.47
    entlich
    0.46
     A
    0.45
     favour
    0.45
    Ä
    0.45
    ์
    0.45
    л
    0.44
    kovic
    0.44
    POSITIVE LOGITS
    ।’
    0.52
     saranam
    0.52
    ’।
    0.52
    otipi
    0.51
     orgasm
    0.51
    ’).
    0.49
    this
    0.48
    তাহাকে
    0.46
    તમાં
    0.46
     وی
    0.46
    Act Density 0.000%

    No Known Activations