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

    Neuronpedia

    INDEX
    Explanations

    changes to or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ազ
    0.30
    का
    0.28
    ゲー
    0.27
    OGRAPHY
    0.26
     популярных
    0.25
    STATE
    0.25
    㴦
    0.25
    这种
    0.24
    లను
    0.24
    کی
    0.23
    POSITIVE LOGITS
     testAvg
    0.28
     ㅛ
    0.28
     covenants
    0.28
     glTex
    0.27
     ы
    0.27
     borrows
    0.27
    š
    0.26
     covalently
    0.26
     fairly
    0.26
    iasco
    0.26
    Act Density 0.092%

    No Known Activations