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

    Neuronpedia

    INDEX
    Explanations

    choosing formality in communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Process
    0.78
    Rite
    0.72
    ๎
    0.71
    Notes
    0.71
    Mark
    0.69
    Satisf
    0.68
     समझे
    0.67
     নিঃস
    0.67
    okines
    0.66
    notes
    0.66
    POSITIVE LOGITS
     সম্রাট
    0.82
     মদ
    0.78
     ingles
    0.76
     энер
    0.75
    クター
    0.72
     ра
    0.71
     खरीदना
    0.71
    órz
    0.70
    หมือน
    0.70
     Inspector
    0.70
    Act Density 0.039%

    No Known Activations