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

    Neuronpedia

    INDEX
    Explanations

    file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpose
    0.25
     propósito
    0.25
     atoi
    0.24
     Purpose
    0.23
    ؤس
    0.22
    яз
    0.22
    purpose
    0.22
     moim
    0.22
     prise
    0.21
    urpose
    0.21
    POSITIVE LOGITS
     முஸ்
    0.27
    ത്തിനെ
    0.25
    簀
    0.25
     हैप्पी
    0.25
     मुस्लिम
    0.25
    crossentropy
    0.24
     swimmer
    0.24
    పు
    0.23
     férias
    0.23
    Ꮭ
    0.23
    Act Density 0.013%

    No Known Activations