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

    Neuronpedia

    INDEX
    Explanations

    identifiers and their values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >∕
    0.32
     polypes
    0.30
    CUSSION
    0.29
     músculos
    0.29
    Jeśli
    0.29
    ObjectTemp
    0.29
    基督
    0.29
    WallArray
    0.28
    VSLU
    0.28
     ऑक्साइड
    0.28
    POSITIVE LOGITS
     (
    0.45
    ,
    0.41
     =
    0.39
     was
    0.35
    ↵
    0.35
     Public
    0.34
        
    0.34
     The
    0.33
    .
    0.33
     It
    0.33
    Act Density 0.287%

    No Known Activations