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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deletes
    -0.09
     Sh
    -0.07
     Deleted
    -0.07
     newObj
    -0.07
    Update
    -0.06
     Cord
    -0.06
    Identifier
    -0.06
    /store
    -0.06
     Xu
    -0.06
    abwe
    -0.06
    POSITIVE LOGITS
    �
    0.07
     faç
    0.07
     IA
    0.06
     ελλην
    0.06
    ाट
    0.06
    тах
    0.06
    -AA
    0.06
     ounce
    0.06
    _HAS
    0.06
    Haz
    0.06
    Act Density 0.057%

    No Known Activations