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

    Neuronpedia

    INDEX
    Explanations

    direct connection or link

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aviation
    0.54
     Wadi
    0.52
     inclement
    0.52
     agua
    0.51
     ander
    0.51
     Uncertain
    0.51
     deixou
    0.50
     अति
    0.50
     eau
    0.50
     inver
    0.50
    POSITIVE LOGITS
     controls
    0.48
     transactions
    0.47
    IER
    0.46
     Forces
    0.46
    AH
    0.44
     MAX
    0.44
     RE
    0.43
    ACT
    0.43
    뽀
    0.41
     respects
    0.41
    Act Density 0.001%

    No Known Activations