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

    Neuronpedia

    INDEX
    Explanations

    current date information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➘
    0.37
    ິງ
    0.36
    Ꭿ
    0.36
    0.36
     spinors
    0.35
    (^
    0.34
    ɕ
    0.34
    GONDOR
    0.34
     সেদিন
    0.34
     কৰি
    0.34
    POSITIVE LOGITS
     Where
    0.43
     evaluating
    0.41
     estimating
    0.40
     AGM
    0.40
    4
    0.39
     agre
    0.38
     oluştur
    0.38
     atualização
    0.38
    ple
    0.37
     where
    0.37
    Act Density 0.019%

    No Known Activations