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

    Neuronpedia

    INDEX
    Explanations

    comin', swirlin', tryin', buildin'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    َة
    0.54
    Tiempo
    0.54
    Э
    0.53
    ísmo
    0.53
     Você
    0.52
    Фото
    0.52
    Ú
    0.51
     ظهور
    0.51
    녈
    0.51
    Fear
    0.51
    POSITIVE LOGITS
     behav
    0.78
     organiz
    0.72
     collabor
    0.71
     appro
    0.70
     repe
    0.68
     develop
    0.68
     exerc
    0.68
     promot
    0.67
     estab
    0.66
     conclud
    0.66
    Act Density 0.060%

    No Known Activations