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

    Neuronpedia

    INDEX
    Explanations

    terms and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    γκα
    0.55
    Gir
    0.43
    Trung
    0.43
     trụ
    0.43
    newTask
    0.43
    𝗠
    0.42
    Mara
    0.42
     गाँ
    0.42
     સફળ
    0.41
    чат
    0.40
    POSITIVE LOGITS
     contains
    0.48
     Image
    0.46
     image
    0.43
     enclosed
    0.43
     Kinetic
    0.42
     of
    0.42
     contain
    0.41
     inside
    0.40
     underneath
    0.39
     connected
    0.39
    Act Density 0.000%

    No Known Activations