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

    Neuronpedia

    INDEX
    Explanations

    computer science and vision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lorem
    0.92
    Luk
    0.85
    Mongo
    0.84
    Fisher
    0.84
    Cru
    0.82
    ानु
    0.80
    फ्त
    0.80
    Airport
    0.79
    Bool
    0.78
    С
    0.77
    POSITIVE LOGITS
     algorithms
    1.33
    ised
    1.33
    械
    1.27
    ية
    1.26
     aided
    1.26
    izadas
    1.23
    ized
    1.21
     wills
    1.16
    izada
    1.16
     computer
    1.16
    Act Density 0.211%

    No Known Activations