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

    Neuronpedia

    INDEX
    Explanations

    access websites and current information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ๊
    0.46
    ႃႇ
    0.46
    COP
    0.45
    IG
    0.45
    тным
    0.43
    Ŵ
    0.43
    Setting
    0.43
     нашем
    0.42
    ～
    0.42
     melody
    0.42
    POSITIVE LOGITS
     tied
    0.46
     теку
    0.43
     toward
    0.42
    场
    0.41
     applied
    0.40
     Toward
    0.40
    场的
    0.40
    [multimodal]
    0.40
     विपक्षी
    0.40
     कोण
    0.40
    Act Density 0.008%

    No Known Activations