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

    Neuronpedia

    INDEX
    Explanations

    security and importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ihrem
    0.49
    ິ
    0.48
     অস্থির
    0.46
     Jeśli
    0.44
    वलं
    0.44
     ungef
    0.44
    ிய
    0.43
    ྥ
    0.42
     ApiResponse
    0.42
     différente
    0.41
    POSITIVE LOGITS
     bona
    0.46
     governance
    0.45
     quintessential
    0.45
     empir
    0.45
     secession
    0.44
     fallacy
    0.44
     başta
    0.43
     sabbatical
    0.43
    UK
    0.43
     statesman
    0.43
    Act Density 0.015%

    No Known Activations