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

    Neuronpedia

    INDEX
    Explanations

    criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mentioned
    -0.08
     інформації
    -0.07
    _transaction
    -0.07
    }).
    -0.06
    story
    -0.06
     presente
    -0.06
     disparities
    -0.06
    570
    -0.06
     bloom
    -0.06
    _over
    -0.06
    POSITIVE LOGITS
     OT
    0.07
     antique
    0.06
    udades
    0.06
     Potion
    0.06
    .appcompat
    0.06
    」↵
    0.06
    ]");↵
    0.06
    .eof
    0.06
     πα
    0.06
    utto
    0.06
    Act Density 0.005%

    No Known Activations