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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     只
    -0.07
    _refs
    -0.07
    Keyword
    -0.06
    asar
    -0.06
     Jamie
    -0.06
     加
    -0.06
    Square
    -0.06
    مة
    -0.06
    _UTILS
    -0.06
     empir
    -0.06
    POSITIVE LOGITS
     cry
    0.07
    authorize
    0.06
     devel
    0.06
     shootout
    0.06
     zest
    0.06
     silly
    0.06
     indexPath
    0.06
    voří
    0.06
     ven
    0.06
     greetings
    0.06
    Act Density 0.003%

    No Known Activations