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

    Neuronpedia

    INDEX
    Explanations

    speeds are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CSS
    0.49
     kleuren
    0.47
     winkel
    0.46
     legal
    0.46
     Schweiz
    0.45
     MPS
    0.44
     SDP
    0.44
     I
    0.44
     LES
    0.43
    愉
    0.43
    POSITIVE LOGITS
    মিটার
    0.63
     खोसला
    0.52
     unsettled
    0.47
     اداکار
    0.47
     ค่ะ
    0.46
     آپریشن
    0.45
     defray
    0.45
     アクセサリー
    0.45
     microwave
    0.45
    MW
    0.44
    Act Density 0.000%

    No Known Activations