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

    Neuronpedia

    INDEX
    Explanations

    Leading by example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flats
    -0.08
     Schwierigkeiten
    -0.08
    .width
    -0.08
    ੱਟ
    -0.08
    TEGR
    -0.08
    .retrieve
    -0.07
     finalist
    -0.07
     transición
    -0.07
    ुध
    -0.07
     Flats
    -0.07
    POSITIVE LOGITS
    榜
    0.09
    姿
    0.09
     lighting
    0.08
     posture
    0.08
     maus
    0.08
     чест
    0.08
     Autumn
    0.08
     보여
    0.08
     persuasive
    0.08
     sobri
    0.08
    Act Density 0.011%

    No Known Activations