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

    Neuronpedia

    INDEX
    Explanations

    ensures whole words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Multiply
    0.41
    ចាយ
    0.39
     backstory
    0.38
     infamous
    0.37
    くらい
    0.37
     необы
    0.37
     Lancet
    0.37
     Incredible
    0.37
     fowl
    0.37
    าส
    0.36
    POSITIVE LOGITS
    ುದ
    0.43
     শান্তিপূর্ণ
    0.43
     gacche
    0.39
     previewBuilder
    0.39
     serving
    0.38
    lake
    0.38
    wpt
    0.38
     మేము
    0.38
     agacch
    0.38
    ierta
    0.38
    Act Density 0.004%

    No Known Activations