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

    Neuronpedia

    INDEX
    Explanations

    amazon web services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matin
    0.71
     reproduce
    0.66
     reproduction
    0.65
     adult
    0.64
     Bing
    0.63
     bing
    0.63
     port
    0.62
     فائ
    0.61
    bing
    0.60
    mitter
    0.60
    POSITIVE LOGITS
    lambda
    0.77
    Mechanical
    0.75
    Lambda
    0.74
    AWS
    0.73
     Lambda
    0.69
     AWS
    0.69
     لیں
    0.67
     lâm
    0.64
     lambda
    0.63
    ας
    0.62
    Act Density 0.058%

    No Known Activations