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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ex
    -0.07
     quant
    -0.07
     tohoto
    -0.06
     foolish
    -0.06
    FileInfo
    -0.06
     lux
    -0.06
    _setopt
    -0.06
    脱
    -0.06
    Fx
    -0.06
     लड़क
    -0.06
    POSITIVE LOGITS
    (_.
    0.07
     Serge
    0.06
    ğit
    0.06
    İs
    0.06
     boarded
    0.06
     ivory
    0.06
    (Display
    0.06
     Narr
    0.06
     componentDidUpdate
    0.06
     Zombie
    0.06
    Act Density 0.273%

    No Known Activations