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

    Neuronpedia

    INDEX
    Explanations

    associated details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    効果
    0.56
    Todos
    0.54
    盱
    0.52
    骈
    0.51
    小説
    0.50
    ó
    0.50
    Canc
    0.49
     चोपड़ा
    0.48
    谶
    0.48
    Gracias
    0.47
    POSITIVE LOGITS
     j
    0.55
     x
    0.50
     (
    0.50
     hexagonal
    0.47
     physic
    0.47
     epoxy
    0.47
     pendant
    0.47
     kir
    0.46
     resin
    0.46
     grouped
    0.45
    Act Density 0.001%

    No Known Activations