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

    Neuronpedia

    INDEX
    Explanations

    following predetermined rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soc
    0.74
     pes
    0.73
     Days
    0.71
     truc
    0.70
     vô
    0.70
     п
    0.67
     tes
    0.66
     musician
    0.66
     fre
    0.66
     Ec
    0.66
    POSITIVE LOGITS
     hospitales
    0.85
     asociaciones
    0.76
    toEqual
    0.75
    вы
    0.75
    ляем
    0.73
    पीजी
    0.73
    केजी
    0.73
     CHARSET
    0.73
    ૧
    0.73
    鉭
    0.73
    Act Density 0.008%

    No Known Activations