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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ECC
    0.60
     হলুদ
    0.59
     PPC
    0.59
     '<%=
    0.57
    ignano
    0.57
    arkhand
    0.57
     Украи
    0.56
     Hello
    0.56
    Qw
    0.56
    Женско
    0.55
    POSITIVE LOGITS
    קת
    0.56
    jud
    0.54
    стане
    0.51
    makeup
    0.50
    רה
    0.49
    bounds
    0.49
     Aut
    0.47
    ework
    0.47
     গর্ব
    0.47
    дка
    0.47
    Act Density 0.000%

    No Known Activations