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

    Neuronpedia

    INDEX
    Explanations

    caret symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    2.05
    ines
    1.66
    ባድ
    1.59
    maßnahmen
    1.58
    ко
    1.56
    िस्ट
    1.56
    นะคะ
    1.54
    ны
    1.53
     congruence
    1.50
    <0x80>
    1.49
    POSITIVE LOGITS
    ہ
    2.78
    ین
    2.63
    드
    2.41
    Meine
    2.27
    А
    2.27
    하는
    2.25
    ia
    2.23
    ME
    2.17
    ई
    2.16
    ad
    2.11
    Act Density 0.007%

    No Known Activations