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

    Neuronpedia

    INDEX
    Explanations

    Needs Assessment, Daily Accrual, Minimax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺖ
    1.69
    𝐭
    1.66
     Morbi
    1.54
     Tregs
    1.48
     ethane
    1.45
     flashbacks
    1.43
     Elys
    1.41
    ৃহে
    1.40
    los
    1.38
     FaceTime
    1.38
    POSITIVE LOGITS
    ’
    1.77
    bild
    1.61
    حدى
    1.41
    います
    1.38
    و
    1.37
    ok
    1.35
    だから
    1.35
    ból
    1.35
    स
    1.33
    ier
    1.31
    Act Density 0.000%

    No Known Activations