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

    Neuronpedia

    INDEX
    Explanations

    spaces and venues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BUN
    0.65
     stanow
    0.64
     trips
    0.63
     medication
    0.63
     spinoff
    0.62
     portfolio
    0.62
     position
    0.61
     pout
    0.61
     অবস্থান
    0.61
     assignments
    0.61
    POSITIVE LOGITS
     hall
    2.82
     Hall
    2.61
    Hall
    2.41
    hall
    2.33
     halls
    2.33
     auditorium
    2.31
     HALL
    2.20
     Auditorium
    2.13
    HALL
    2.11
     Halls
    2.10
    Act Density 0.116%

    No Known Activations