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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nons
    0.38
     Put
    0.37
    ↵↵↵↵
    0.37
    ට්
    0.37
    ↵↵
    0.35
     Sent
    0.35
     Hive
    0.35
     SS
    0.35
     Majority
    0.34
     مار
    0.34
    POSITIVE LOGITS
    Jeśli
    0.42
    ബരി
    0.39
    Ble
    0.38
     eğer
    0.37
    ოლო
    0.37
    ⸨
    0.36
    Ко
    0.36
     нещо
    0.36
    さい
    0.35
    сель
    0.35
    Act Density 0.031%

    No Known Activations