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

    Neuronpedia

    INDEX
    Explanations

    assigning default values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anschließend
    2.34
    USAGE
    2.29
    ू
    2.29
    st
    2.28
    z
    2.27
     opis
    2.26
     gesehen
    2.26
     encima
    2.19
     unité
    2.17
    olda
    2.15
    POSITIVE LOGITS
    😂😂
    2.89
    с
    2.70
    нце
    2.57
    व
    2.50
    гү
    2.50
    𝘱
    2.46
    𝘪
    2.42
    வும்
    2.38
    tttt
    2.33
    تون
    2.31
    Act Density 0.031%

    No Known Activations