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

    Neuronpedia

    INDEX
    Explanations

    TypeError, Python indexing, Spanish phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     representatives
    0.70
     compromises
    0.68
     compromise
    0.67
    ඥ
    0.66
     supermarkets
    0.66
     peas
    0.65
     campaigners
    0.64
    phill
    0.62
     аст
    0.62
     Representatives
    0.62
    POSITIVE LOGITS
     essi
    0.82
     Induced
    0.77
     они
    0.76
    relation
    0.75
     tragedies
    0.75
    他們
    0.74
     він
    0.74
     পড়া
    0.74
    情节
    0.74
     ocurrido
    0.74
    Act Density 0.001%

    No Known Activations