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

    Neuronpedia

    INDEX
    Explanations

    Dockerfile commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cited
    0.43
     ആദ്യ
    0.41
     vertebra
    0.41
     peral
    0.41
    ومه
    0.41
     बाबू
    0.41
    不见
    0.40
    志森
    0.38
    न्देल
    0.38
     mappa
    0.38
    POSITIVE LOGITS
    eslint
    0.50
    ul
    0.43
    co
    0.43
    ere
    0.42
    ern
    0.42
    al
    0.41
    ip
    0.41
    ta
    0.40
    nan
    0.40
    `-
    0.40
    Act Density 0.000%

    No Known Activations