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

    Neuronpedia

    INDEX
    Explanations

    number followed by slash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocene
    0.68
    प्लेक्स
    0.67
     past
    0.62
    حات
    0.62
     Proposals
    0.62
    ispo
    0.61
     Luxe
    0.60
     prairies
    0.60
     usados
    0.60
    risis
    0.60
    POSITIVE LOGITS
     এটাও
    0.69
     habt
    0.68
     ascertaining
    0.66
     داشته
    0.65
     euer
    0.63
     pot
    0.63
    ñ
    0.63
    āk
    0.62
     अगदी
    0.61
     کې
    0.61
    Act Density 0.007%

    No Known Activations