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
     контакт
    -0.08
     bulshada
    -0.07
     Kurt
    -0.07
     sample
    -0.07
     Danny
    -0.07
    ))↵↵↵
    -0.07
     crossover
    -0.07
    નો
    -0.07
     ಫಲ
    -0.07
     નોંધ
    -0.07
    POSITIVE LOGITS
     strcat
    0.09
     Editions
    0.08
    燕
    0.08
     extravag
    0.08
    ம்பெ
    0.08
     //'
    0.08
    .Middle
    0.08
    藏
    0.07
     Klassiker
    0.07
    aliwa
    0.07
    Act Density 0.000%

    No Known Activations