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

    Neuronpedia

    INDEX
    Explanations

    iterator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cars
    -0.09
    Foods
    -0.08
     nouns
    -0.08
    Coach
    -0.08
    స
    -0.08
     Cars
    -0.07
    Iterations
    -0.07
     Foods
    -0.07
     taught
    -0.07
    రిక
    -0.07
    POSITIVE LOGITS
    ológicas
    0.09
    ológico
    0.09
     }
↵
    0.08
     }
↵
↵
    0.08
    .nil
    0.08
     Eph
    0.08
     Atl
    0.08
    ijer
    0.08
    }`;↵↵
    0.08
     sozinho
    0.08
    Act Density 0.001%

    No Known Activations