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

    Neuronpedia

    INDEX
    Explanations

    CAT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mod
    -0.07
    英語
    -0.07
    saldo
    -0.06
     analytics
    -0.06
    istributor
    -0.06
     rodi
    -0.06
    _INVALID
    -0.06
     culinary
    -0.06
     удар
    -0.06
    'autres
    -0.06
    POSITIVE LOGITS
    /class
    0.06
    cord
    0.06
     Rapids
    0.06
    фф
    0.06
    _approved
    0.06
     grupo
    0.06
     JFrame
    0.06
     JAXB
    0.06
    .jpa
    0.06
     tempting
    0.06
    Act Density 0.001%

    No Known Activations