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

    Neuronpedia

    INDEX
    Explanations

    support helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑫
    0.85
    geç
    0.80
    ник
    0.80
     হইত
    0.79
     decontamination
    0.78
     Ger
    0.77
     Doubt
    0.77
    Mailer
    0.77
     Macedonia
    0.77
     Giac
    0.75
    POSITIVE LOGITS
     otherwise
    0.69
     जरूर
    0.63
     faster
    0.63
     arms
    0.62
     chemically
    0.62
    轧
    0.62
     '=',
    0.60
     latent
    0.60
     processes
    0.59
     विजिट
    0.59
    Act Density 0.027%

    No Known Activations