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

    Neuronpedia

    INDEX
    Explanations

    programming and data analysis terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    圩
    0.54
    ほぼ
    0.46
    Terminal
    0.45
    Named
    0.45
     거의
    0.44
    ലിം
    0.44
     होके
    0.44
    生まれた
    0.43
    زيز
    0.43
    terminal
    0.42
    POSITIVE LOGITS
    osy
    0.53
     Hester
    0.52
     Gund
    0.48
     brow
    0.48
     Impact
    0.48
     Impacts
    0.47
    雋
    0.47
     stra
    0.47
     essays
    0.46
     romances
    0.46
    Act Density 0.000%

    No Known Activations