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

    Neuronpedia

    INDEX
    Explanations

    take it personally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marsh
    0.42
    ເລ
    0.42
    dec
    0.41
    တွင်
    0.39
    хь
    0.38
     Бере
    0.38
    ளில்
    0.38
    configure
    0.38
     ब्यू
    0.38
    aine
    0.37
    POSITIVE LOGITS
     pills
    0.41
     notes
    0.40
     showers
    0.40
     snacks
    0.39
    बास
    0.39
    ватися
    0.38
     Notes
    0.38
    INIS
    0.38
     inaccur
    0.37
     breaths
    0.37
    Act Density 0.005%

    No Known Activations