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

    Neuronpedia

    INDEX
    Explanations

    promoting positive or harmful outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     implications
    0.51
     Implications
    0.47
     intentar
    0.45
    :"+
    0.42
     Impact
    0.41
     determinar
    0.40
    Impact
    0.39
    imposed
    0.39
     meghatá
    0.39
    インパクト
    0.39
    POSITIVE LOGITS
     growth
    0.68
     awareness
    0.63
     crescimento
    0.58
     uptake
    0.57
     healthy
    0.57
     innovation
    0.55
     creativity
    0.55
     wzrost
    0.55
    growth
    0.54
     togetherness
    0.54
    Act Density 0.020%

    No Known Activations