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

    Neuronpedia

    INDEX
    Explanations

    questions and question types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    те
    1.98
    на
    1.48
    л
    1.42
    ন
    1.41
    ン
    1.38
    न
    1.38
    ле
    1.36
    ে
    1.36
    ко
    1.30
    ა
    1.23
    POSITIVE LOGITS
    naires
    1.57
    luğ
    1.34
    scientist
    1.24
    ned
    1.22
    𝐭
    1.19
    함으로써
    1.18
     carbides
    1.16
    Descrição
    1.16
     tunneling
    1.14
    netje
    1.13
    Act Density 0.000%

    No Known Activations