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

    Neuronpedia

    INDEX
    Explanations

    modelmodel predictions or outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rea
    0.42
    fers
    0.42
    äm
    0.41
    gin
    0.40
    ping
    0.40
    :.
    0.40
    ៖
    0.40
    bib
    0.40
    :
    0.40
    ä
    0.40
    POSITIVE LOGITS
     ஆலய
    0.48
     comulti
    0.46
     flanked
    0.46
     popupButton
    0.45
     коронави
    0.44
     प्राइमरी
    0.44
     theseKeys
    0.44
     निर्माता
    0.43
     ഇവിടെ
    0.42
    Ⅴ
    0.42
    Act Density 0.001%

    No Known Activations