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

    Neuronpedia

    INDEX
    Explanations

    describing context and setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    妪
    0.48
     Dend
    0.41
     murderous
    0.41
     Murder
    0.40
     businessmen
    0.40
     pêche
    0.40
     Instinct
    0.40
     വ്യാ
    0.40
     Tolkien
    0.40
     Paint
    0.39
    POSITIVE LOGITS
     banget
    0.49
     bahkan
    0.48
     equivale
    0.47
     ingresar
    0.46
    AH
    0.46
    *,
    0.46
     cáps
    0.46
    και
    0.45
     allere
    0.45
    non
    0.44
    Act Density 0.002%

    No Known Activations