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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اع
    -0.07
     referencia
    -0.07
    conj
    -0.07
     sí
    -0.06
    lük
    -0.06
    Вт
    -0.06
     Terrain
    -0.06
     mechanics
    -0.06
     listop
    -0.06
    э
    -0.06
    POSITIVE LOGITS
    .styles
    0.07
    ,last
    0.07
    GR
    0.07
    .detach
    0.06
     Formation
    0.06
     consistently
    0.06
     directly
    0.06
     clock
    0.06
    _Cancel
    0.06
    icity
    0.06
    Act Density 0.054%

    No Known Activations