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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एवं
    0.92
     наиболее
    0.80
     अधिकांश
    0.79
     niewiel
    0.75
     számos
    0.74
     však
    0.74
     yalnızca
    0.74
    primarily
    0.73
    เพียง
    0.72
    Perhaps
    0.72
    POSITIVE LOGITS
     thing
    1.76
     stupid
    1.66
     crappy
    1.43
     crap
    1.41
     bullshit
    1.39
     dudes
    1.38
     weird
    1.35
     stuff
    1.34
     damn
    1.34
     shitty
    1.33
    Act Density 0.138%

    No Known Activations