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

    Neuronpedia

    INDEX
    Explanations

    significant and substantial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     উঠিয়া
    0.57
     Damn
    0.56
     Alone
    0.56
     Remover
    0.56
    那个
    0.55
     baratos
    0.55
     Basics
    0.54
    zigen
    0.54
    olato
    0.54
     같
    0.54
    POSITIVE LOGITS
     significant
    2.95
     substantial
    2.53
    significant
    2.44
     considerable
    2.37
    Significant
    2.31
     Significant
    2.28
     significativa
    2.10
    substantial
    2.05
     significativo
    2.05
     значи
    2.05
    Act Density 1.941%

    No Known Activations