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

    Neuronpedia

    INDEX
    Explanations

    hydraulic calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÉRI
    0.42
     Кор
    0.41
    Кор
    0.41
     တော့
    0.40
    稈
    0.40
    ."]
    0.37
    ensión
    0.36
    ÁN
    0.36
    ारी
    0.35
     zahlen
    0.35
    POSITIVE LOGITS
    <start_of_image>
    0.46
    ↵↵↵↵↵↵↵↵↵
    0.42
     hearts
    0.41
     imid
    0.40
     Hearts
    0.40
     heartily
    0.39
     Himmel
    0.39
     Guar
    0.38
    ↵↵↵↵
    0.38
    ↵↵↵↵↵↵↵↵↵↵
    0.38
    Act Density 0.000%

    No Known Activations