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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parad
    -0.07
    .Ct
    -0.07
    _jet
    -0.07
    @Entity
    -0.06
     defence
    -0.06
     guardians
    -0.06
    ushort
    -0.06
    .Direct
    -0.06
     náro
    -0.06
    อส
    -0.06
    POSITIVE LOGITS
     cling
    0.07
     Newly
    0.06
     sitesi
    0.06
    inel
    0.06
     hive
    0.06
    _cid
    0.06
     Twenty
    0.06
     cra
    0.06
    クション
    0.06
    лении
    0.06
    Act Density 0.001%

    No Known Activations