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

    Neuronpedia

    INDEX
    Explanations

    action completion indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েল
    0.65
     DENUMIRE
    0.64
    𒈨
    0.60
    まぁ
    0.59
    テナンス
    0.57
    Año
    0.57
     searchValue
    0.57
     bě
    0.57
    DeleteDialogOpen
    0.57
    треб
    0.57
    POSITIVE LOGITS
     via
    0.69
     với
    0.64
     with
    0.63
    q
    0.63
    í
    0.61
    da
    0.61
     Bugs
    0.61
    ids
    0.59
     VIA
    0.59
     उत्सुक
    0.59
    Act Density 0.542%

    No Known Activations