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

    Neuronpedia

    INDEX
    Explanations

    instructions or reminders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    チュラル
    0.36
    /=
    0.36
    жидан
    0.35
     うん
    0.34
     pengukuran
    0.34
    фона
    0.34
    ⅙
    0.34
    ettamente
    0.33
    ¹)
    0.33
    ⅛
    0.33
    POSITIVE LOGITS
     Notice
    0.75
     Note
    0.71
     notice
    0.66
     Replace
    0.65
     Please
    0.64
    Notice
    0.62
    Note
    0.59
     Make
    0.58
    Make
    0.58
     Remember
    0.57
    Act Density 0.067%

    No Known Activations