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

    Neuronpedia

    INDEX
    Explanations

    tracking, yourself, and risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    员
    0.40
     Agenda
    0.40
     Kiss
    0.38
     Carmen
    0.38
    idmat
    0.38
    বদ
    0.37
    岑
    0.37
    浾
    0.37
    会的
    0.36
    社会的
    0.36
    POSITIVE LOGITS
    Component
    0.46
    െങ്ക
    0.43
     fallback
    0.41
     একক
    0.41
     classroom
    0.40
     তুলনায়
    0.39
     unbounded
    0.38
    classroom
    0.38
    >(
    0.38
    heuristic
    0.38
    Act Density 0.000%

    No Known Activations