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

    Neuronpedia

    INDEX
    Explanations

    equals signs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udson
    -0.07
    defined
    -0.07
     Contr
    -0.07
    prowadził
    -0.07
     transforming
    -0.07
    になりました
    -0.07
    _typ
    -0.06
    áf
    -0.06
    的方法
    -0.06
    𫟼
    -0.06
    POSITIVE LOGITS
    bags
    0.08
     Politico
    0.07
    Position
    0.07
     dim
    0.07
     vbox
    0.07
     default
    0.07
     prote
    0.07
     curl
    0.07
    azar
    0.07
    'url
    0.07
    Act Density 0.001%

    No Known Activations

    This feature has no known activations.