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

    Neuronpedia

    INDEX
    Explanations

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     நகர
    -0.09
     magaalada
    -0.08
     பட
    -0.08
    Shortest
    -0.08
    _extended
    -0.08
     адказ
    -0.08
    Ten
    -0.08
     Ten
    -0.07
     அந்த
    -0.07
     നഗ
    -0.07
    POSITIVE LOGITS
    天然
    0.10
     naturelles
    0.09
     remedies
    0.09
     herbal
    0.09
     натураль
    0.09
     naturels
    0.08
    版
    0.08
     substitutions
    0.08
     autant
    0.08
    自然
    0.08
    Act Density 0.022%

    No Known Activations