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

    Neuronpedia

    INDEX
    Explanations

    talking to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    3.29
    .
    3.03
    (
    2.85
    '
    2.59
    、
    2.55
    =
    2.50
    ’
    2.49
     organisation
    2.48
    /
    2.45
    タック
    2.33
    POSITIVE LOGITS
    rinsic
    3.39
    7
    3.20
     fizik
    3.13
    req
    2.91
    abhut
    2.87
    6
    2.86
     инфра
    2.85
    quetas
    2.84
    Diffuse
    2.84
    8
    2.84
    Act Density 0.591%

    No Known Activations