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

    Neuronpedia

    INDEX
    Explanations

    superlatives and extremes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UST
    0.95
    ان
    0.94
    ERI
    0.90
    Tính
    0.86
    உலக
    0.86
     tourisme
    0.85
    ט
    0.83
    CLUDES
    0.83
    스타그램
    0.82
    Grande
    0.82
    POSITIVE LOGITS
     possible
    2.10
     Possible
    1.69
     POSSIBLE
    1.65
    possible
    1.55
     posible
    1.52
    Possible
    1.42
     possibles
    1.39
     possibile
    1.35
     posibles
    1.32
     возмо
    1.29
    Act Density 0.246%

    No Known Activations