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

    Neuronpedia

    INDEX
    Explanations

    titles after "the" or "named"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manly
    0.56
     partying
    0.50
     tummy
    0.50
     parody
    0.47
     macho
    0.47
     nipp
    0.46
     goodies
    0.46
     mommy
    0.45
     poodle
    0.45
     lube
    0.45
    POSITIVE LOGITS
     librarians
    0.54
    Botan
    0.54
     lighthouse
    0.52
     Archiv
    0.52
     nineteen
    0.52
     botan
    0.51
     Botan
    0.50
     apprenticeship
    0.50
    Library
    0.49
     seventeen
    0.48
    Act Density 0.043%

    No Known Activations