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

    Neuronpedia

    INDEX
    Explanations

    configuration and customization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atrice
    0.46
    conjugated
    0.44
    ત્તા
    0.43
     verstehen
    0.43
     сопро
    0.42
     conocimiento
    0.42
    emotional
    0.42
     unscathed
    0.42
    neu
    0.42
     narrative
    0.41
    POSITIVE LOGITS
     Settings
    0.70
     settings
    0.70
     default
    0.69
     Customize
    0.66
    配置
    0.65
     настрой
    0.64
     customise
    0.64
     konfigur
    0.63
     настройки
    0.63
    默认
    0.63
    Act Density 0.181%

    No Known Activations