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

    Neuronpedia

    INDEX
    Explanations

    okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MsgCallBack
    0.77
     paréntesis
    0.72
    펌
    0.72
    💇
    0.71
    যান
    0.71
     transportasi
    0.71
     presentato
    0.71
    یسم
    0.71
     fracking
    0.70
     staffing
    0.69
    POSITIVE LOGITS
     let
    0.66
     Let
    0.66
    Let
    0.60
     रहने
    0.51
    чета
    0.49
     Selamat
    0.49
     your
    0.49
     lets
    0.47
    лето
    0.47
    let
    0.46
    Act Density 0.100%

    No Known Activations