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

    Neuronpedia

    INDEX
    Explanations

    website: url

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     murderous
    0.69
     pathogenesis
    0.66
     tyrannical
    0.64
     algoritmo
    0.64
     halluc
    0.63
     ataques
    0.63
     futile
    0.63
     ataque
    0.62
     flawed
    0.62
     epistem
    0.61
    POSITIVE LOGITS
     Website
    0.84
    Website
    0.82
     website
    0.80
    是一家
    0.79
    website
    0.78
     services
    0.78
     Yelp
    0.74
     услуг
    0.73
     dealership
    0.71
     servicios
    0.69
    Act Density 0.374%

    No Known Activations