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

    Neuronpedia

    INDEX
    Explanations

    process and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ંડ
    0.43
    রস
    0.43
    fony
    0.41
    ूद
    0.40
    événement
    0.39
    錆
    0.39
    ราม
    0.38
    fon
    0.38
    ىن
    0.38
    इका
    0.38
    POSITIVE LOGITS
     Spice
    0.41
     Check
    0.40
     Wave
    0.40
     Sp
    0.40
     wave
    0.39
     Merchandise
    0.38
    wave
    0.38
     nal
    0.37
     Join
    0.37
    波
    0.36
    Act Density 0.001%

    No Known Activations