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

    Neuronpedia

    INDEX
    Explanations

    special stories and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estética
    0.53
     iteratively
    0.52
     merda
    0.50
     hyperlocal
    0.48
     laterally
    0.47
     dude
    0.46
     conceptually
    0.46
     decently
    0.46
    нтен
    0.46
     tbh
    0.46
    POSITIVE LOGITS
     wonderful
    0.90
    wonderful
    0.77
     special
    0.66
     amazing
    0.64
     marvelous
    0.64
     Wonderful
    0.62
     adventures
    0.60
    Wonderful
    0.60
     little
    0.57
     lovely
    0.56
    Act Density 0.023%

    No Known Activations