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

    Neuronpedia

    INDEX
    Explanations

    ratings out of 5 stars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allergenic
    0.44
    িয়৷
    0.43
     حكوم
    0.42
     ☐
    0.42
    three
    0.41
     :");
    0.40
    igenza
    0.40
    two
    0.40
    urcharge
    0.39
     ऑब्जेक्ट
    0.39
    POSITIVE LOGITS
    ENDED
    0.39
    қты
    0.38
     Overall
    0.37
    setFont
    0.35
     Happy
    0.34
    لیل
    0.34
    見
    0.34
     involving
    0.34
     explicitly
    0.33
     Fonte
    0.33
    Act Density 0.030%

    No Known Activations