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

    Neuronpedia

    INDEX
    Explanations

    Object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neighboring
    -0.07
    Adjacent
    -0.07
    州
    -0.07
     Koh
    -0.06
    -lang
    -0.06
    Selector
    -0.06
    umann
    -0.06
     psi
    -0.06
     Closing
    -0.06
    wi
    -0.06
    POSITIVE LOGITS
     Directions
    0.07
    ernity
    0.06
    กรณ
    0.06
    ature
    0.06
    ασία
    0.06
    ी,
    0.06
     можливість
    0.06
    usterity
    0.06
     editar
    0.06
     irrespective
    0.06
    Act Density 0.003%

    No Known Activations