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

    Neuronpedia

    INDEX
    Explanations

    javascript .map() function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     দুর্দান্ত
    0.47
     čtyř
    0.44
    тай
    0.40
    ၼ်
    0.39
    ęg
    0.39
     četiri
    0.39
     Danes
    0.39
     ()
    0.38
     тря
    0.38
    )()
    0.38
    POSITIVE LOGITS
     item
    0.45
    (([
    0.42
    Keys
    0.41
     Persona
    0.41
     persona
    0.40
    Indexed
    0.39
    ঘরের
    0.39
     dr
    0.39
    (&:
    0.38
    InputElement
    0.37
    Act Density 0.005%

    No Known Activations