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

    Neuronpedia

    INDEX
    Explanations

    a large amount of creations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voicemail
    0.92
     садо
    0.77
     Пусть
    0.76
     tastes
    0.75
     folate
    0.75
     همیشه
    0.74
     центр
    0.74
     الصور
    0.74
     문자
    0.74
     ആദ്യം
    0.74
    POSITIVE LOGITS
    mehr
    0.89
    gebied
    0.85
    ge
    0.83
    libs
    0.73
    zwischen
    0.73
    ش
    0.72
    рили
    0.71
    LOS
    0.71
    estens
    0.70
     rifless
    0.70
    Act Density 0.001%

    No Known Activations