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

    Neuronpedia

    INDEX
    Explanations

    numbers as identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tır
    0.50
    不久
    0.46
    𝒇
    0.45
    CUSSION
    0.44
    vrir
    0.42
    URCH
    0.42
    ambique
    0.41
     Texte
    0.41
     Spannung
    0.41
    ું
    0.41
    POSITIVE LOGITS
    0
    0.63
    Про
    0.52
    मैं
    0.52
    О
    0.51
    1
    0.50
    एक
    0.49
    Ко
    0.49
    Е
    0.49
    Но
    0.48
    Пре
    0.48
    Act Density 0.007%

    No Known Activations