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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment and interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Let
    0.59
    Largest
    0.58
    Quality
    0.55
    Debt
    0.55
    aterials
    0.55
    Satellite
    0.55
    Relative
    0.54
    Genetic
    0.54
    Problems
    0.53
    >,
    0.52
    POSITIVE LOGITS
     positive
    0.75
     positivo
    0.64
    ر
    0.63
     Positive
    0.62
     smiling
    0.62
     positiva
    0.60
     favourable
    0.59
     positivity
    0.58
     positivas
    0.57
     positively
    0.56
    Act Density 0.367%

    No Known Activations