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

    Neuronpedia

    INDEX
    Explanations

    technical concepts and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ா
    0.49
    цент
    0.49
    u
    0.45
    ust
    0.45
    riamo
    0.44
    整理
    0.43
    нице
    0.43
    ллина
    0.43
    ittances
    0.42
    шке
    0.42
    POSITIVE LOGITS
     não
    0.45
     없습니다
    0.43
     Atletico
    0.43
     everytime
    0.42
    你不
    0.42
     Não
    0.41
     insc
    0.41
     boca
    0.41
    拦截
    0.41
     brutally
    0.40
    Act Density 0.000%

    No Known Activations