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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     princess
    -0.06
     místa
    -0.06
     comerc
    -0.06
     granted
    -0.06
     pope
    -0.06
    陆
    -0.06
     vot
    -0.06
     beautiful
    -0.06
     возможности
    -0.06
    )];
↵
    -0.06
    POSITIVE LOGITS
    .model
    0.07
    },{"
    0.07
    OPTION
    0.06
    leep
    0.06
     summarizes
    0.06
     Settlement
    0.06
     fik
    0.06
    ython
    0.06
    intestinal
    0.06
    inator
    0.06
    Act Density 0.039%

    No Known Activations