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

    Neuronpedia

    INDEX
    Explanations

    `url` `link` `services`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sediments
    0.91
     grains
    0.89
     evaded
    0.86
     covariance
    0.85
     castes
    0.85
     habitats
    0.83
     coals
    0.83
     arrows
    0.78
     soils
    0.78
     ammo
    0.78
    POSITIVE LOGITS
     ดู
    0.92
    ﺪ
    0.91
    ﻤ
    0.86
    гар
    0.84
    께
    0.84
    ﺘ
    0.84
    графі
    0.83
    ț
    0.82
    top
    0.82
    ці
    0.82
    Act Density 0.000%

    No Known Activations