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

    Neuronpedia

    INDEX
    Explanations

    apologize for inconvenience this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chợ
    0.41
    OrElse
    0.40
     ввести
    0.39
     heterocyclic
    0.39
    henium
    0.39
     vouloir
    0.39
     persistently
    0.39
     defeat
    0.38
    ્રોલ
    0.38
     তাহলে
    0.38
    POSITIVE LOGITS
    嘮
    0.42
     kol
    0.41
     SAINT
    0.41
     tumorigen
    0.40
    BOOK
    0.40
    scre
    0.39
     GO
    0.39
    pInBuffer
    0.39
    唠
    0.38
     イメージ
    0.38
    Act Density 0.003%

    No Known Activations