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

    Neuronpedia

    INDEX
    Explanations

    wikipedia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    soever
    0.77
     prevista
    0.69
    в
    0.67
    ர்ஸ்
    0.67
     nrow
    0.66
     offsetX
    0.65
    툐
    0.65
     btw
    0.64
     फसलों
    0.63
     supposing
    0.63
    POSITIVE LOGITS
    im
    0.72
     suffice
    0.62
     стать
    0.59
     kapp
    0.58
    Sophie
    0.56
    PP
    0.55
    cdots
    0.54
    endTime
    0.54
    harmony
    0.54
    hander
    0.54
    Act Density 0.087%

    No Known Activations