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

    Neuronpedia

    INDEX
    Explanations

    IPOs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commentaire
    -0.07
    ()->
    -0.07
    [loc
    -0.06
     Pour
    -0.06
     xbmc
    -0.06
    ी,
    -0.06
     simulator
    -0.06
    _integer
    -0.06
    �
    -0.06
     TVs
    -0.06
    POSITIVE LOGITS
    ök
    0.07
    Government
    0.07
    government
    0.07
    hic
    0.06
    having
    0.06
     없
    0.06
    _SN
    0.06
     ave
    0.06
    .tagName
    0.06
     bron
    0.06
    Act Density 0.069%

    No Known Activations