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

    Neuronpedia

    INDEX
    Explanations

    actions and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ｅ
    0.49
    蹦
    0.46
    ით
    0.45
    ੇ
    0.45
    佐
    0.43
    決
    0.43
    ार्ट
    0.42
    ［
    0.42
     $(
    0.42
    افي
    0.42
    POSITIVE LOGITS
     slat
    0.50
     transparencia
    0.49
     imó
    0.48
     costruzione
    0.47
     cherish
    0.47
     campeón
    0.45
     எப்போதும்
    0.45
     innen
    0.44
     receitas
    0.44
     remedi
    0.44
    Act Density 0.000%

    No Known Activations