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

    Neuronpedia

    INDEX
    Explanations

    names or origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indentLevel
    0.25
    iterable
    0.24
    params
    0.24
    parameter
    0.24
    weight
    0.23
    neapolis
    0.23
    🤨
    0.23
    汔
    0.22
    parameters
    0.22
    Serialization
    0.22
    POSITIVE LOGITS
     F
    0.36
     S
    0.36
     P
    0.34
     aptly
    0.33
     L
    0.33
     eponymous
    0.31
     bernama
    0.31
     B
    0.31
     G
    0.30
     C
    0.30
    Act Density 0.312%

    No Known Activations