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

    Neuronpedia

    INDEX
    Explanations

    data identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ire
    0.40
    concent
    0.39
    rated
    0.37
    sl
    0.36
     Poz
    0.36
    蝸
    0.36
    anyon
    0.36
     ಮಿಶ್ರ
    0.36
    არა
    0.35
    allow
    0.35
    POSITIVE LOGITS
    ScriptInterface
    0.48
    AssetDiscovery
    0.44
     बुद्धि
    0.42
    なわち
    0.41
    个性
    0.40
    监
    0.40
     lLoginID
    0.39
     felicidade
    0.39
    Docs
    0.39
    Microelectronics
    0.39
    Act Density 0.141%

    No Known Activations