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

    Neuronpedia

    INDEX
    Explanations

    Isolation, disconnection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (typ
    -0.07
    (ع
    -0.06
    ’acc
    -0.06
     années
    -0.06
    似乎
    -0.06
     НА
    -0.06
     Aunt
    -0.06
     ACA
    -0.06
    лам
    -0.06
    _CLOSE
    -0.06
    POSITIVE LOGITS
    ihan
    0.07
     XmlDocument
    0.06
    _con
    0.06
    ytut
    0.06
    _FILENAME
    0.06
    cluir
    0.06
     insurg
    0.06
     mixins
    0.06
     teslim
    0.06
    .firestore
    0.06
    Act Density 0.183%

    No Known Activations