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

    Neuronpedia

    INDEX
    Explanations

    academic publishing identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اري
    0.30
    などを
    0.28
    اری
    0.27
    metry
    0.27
    או
    0.27
    ण्या
    0.26
    গ্রাম
    0.26
     있고
    0.26
     valued
    0.26
    графи
    0.26
    POSITIVE LOGITS
     doi
    0.42
     preprint
    0.40
    doi
    0.40
    DOI
    0.37
    PAssignment
    0.36
    pdf
    0.35
     manuscript
    0.35
     опубликован
    0.35
     PMID
    0.34
    arxiv
    0.33
    Act Density 0.002%

    No Known Activations