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

    Neuronpedia

    INDEX
    Explanations

    which items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Neues
    0.39
    ího
    0.38
    >[
    0.38
     something
    0.37
    Something
    0.37
    Alternatives
    0.36
     Something
    0.36
    itale
    0.36
     faits
    0.35
     Alternatives
    0.34
    POSITIVE LOGITS
    哪些
    1.50
     quais
    1.44
     какие
    1.37
    Какие
    1.34
     Какие
    1.30
     cuáles
    1.25
     quels
    1.23
     vilka
    1.20
    どの
    1.19
     hvil
    1.16
    Act Density 0.056%

    No Known Activations