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

    Neuronpedia

    INDEX
    Explanations

    standalone prompts or programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    1.10
    u
    0.88
     to
    0.84
     of
    0.80
     ២
    0.79
    ,
    0.79
    𝟐
    0.79
     〢
    0.79
     Đấy
    0.75
    arım
    0.71
    POSITIVE LOGITS
    م
    1.13
    os
    1.01
    وس
    0.96
     geodes
    0.87
    as
    0.86
     inverter
    0.81
    غ
    0.80
     standalone
    0.79
    м
    0.79
     freestanding
    0.78
    Act Density 0.002%

    No Known Activations