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

    Neuronpedia

    INDEX
    Explanations

    non IID data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गला
    0.37
     dedicated
    0.37
    椅子
    0.36
     reflectivity
    0.35
    嘉
    0.35
     dedication
    0.35
    扇
    0.34
     Rabbi
    0.34
    cdt
    0.34
     মন্
    0.34
    POSITIVE LOGITS
     DRM
    0.41
    ynitrite
    0.38
    waves
    0.37
     wave
    0.37
    anshi
    0.37
    oush
    0.36
    waved
    0.36
     பாபிலோ
    0.36
     handed
    0.36
     diperoleh
    0.36
    Act Density 0.003%

    No Known Activations