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

    Neuronpedia

    INDEX
    Explanations

    surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DataBase
    -0.08
     Wichita
    -0.07
     pháp
    -0.06
    Know
    -0.06
     Bowie
    -0.06
    ups
    -0.06
    _tracker
    -0.06
    -To
    -0.06
    Flying
    -0.06
    Endpoints
    -0.06
    POSITIVE LOGITS
     cliffs
    0.07
    .ImageLayout
    0.06
     лиш
    0.06
    argout
    0.06
    villa
    0.06
     profession
    0.06
    mania
    0.06
     όλα
    0.06
    (Id
    0.06
    _MAJOR
    0.06
    Act Density 0.063%

    No Known Activations