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

    Neuronpedia

    INDEX
    Explanations

    você aborda a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Пусть
    0.39
     huyết
    0.38
    ulloch
    0.37
    lassical
    0.37
     kiosk
    0.37
     +:+
    0.36
    پلز
    0.36
     "?"]
    0.36
    tha
    0.36
     एन्
    0.36
    POSITIVE LOGITS
    Waters
    0.40
    Parte
    0.39
    Shore
    0.39
     parte
    0.38
    parte
    0.38
    Wa
    0.37
     shore
    0.37
    ដោយ
    0.37
     기다
    0.37
    Segment
    0.36
    Act Density 0.000%

    No Known Activations