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

    Neuronpedia

    INDEX
    Explanations

    Cohousing, likelihood, dioxide, Status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsdelivr
    0.55
     csrf
    0.53
     gooey
    0.51
     serializer
    0.51
     magnetization
    0.50
     ഓൺലൈ
    0.50
     financeira
    0.50
     materi
    0.49
     ఆర్థిక
    0.48
     linearized
    0.48
    POSITIVE LOGITS
    -
    0.53
    気
    0.51
    恥
    0.49
    י
    0.49
    сті
    0.48
    ור
    0.47
    ви
    0.46
    קי
    0.45
    ઠ
    0.45
     Estr
    0.45
    Act Density 0.001%

    No Known Activations