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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    each
    -0.07
     podí
    -0.06
    Ob
    -0.06
    cih
    -0.06
    Sprite
    -0.06
     shortfall
    -0.06
    Female
    -0.06
     également
    -0.06
    able
    -0.06
     guessing
    -0.06
    POSITIVE LOGITS
     Hampton
    0.06
     Weak
    0.06
    (','
    0.06
     seçenek
    0.06
     Δή
    0.06
    �
    0.06
     bourgeoisie
    0.06
    _bloc
    0.06
     CELL
    0.06
     Arrange
    0.06
    Act Density 0.020%

    No Known Activations