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

    Neuronpedia

    INDEX
    Explanations

    asymptotes or edges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    енты
    0.50
     მე
    0.49
     pól
    0.48
     gratuito
    0.46
     changé
    0.45
     preocup
    0.45
     потому
    0.45
    ൫
    0.44
     所以
    0.44
     reti
    0.43
    POSITIVE LOGITS
    Thursday
    0.50
    Attendees
    0.42
    Each
    0.42
    }$,
    0.42
    Week
    0.41
     உள்ளிட்ட
    0.40
    Rs
    0.39
    Check
    0.39
    Hour
    0.39
    Day
    0.39
    Act Density 0.001%

    No Known Activations