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

    Neuronpedia

    INDEX
    Explanations

    words starting with Ad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pentes
    0.65
     mandates
    0.63
     whistles
    0.63
    corpor
    0.62
     республики
    0.62
    пере
    0.61
     Spain
    0.61
     xy
    0.61
    ห
    0.61
     chaperone
    0.61
    POSITIVE LOGITS
     hoc
    1.11
    hoc
    1.10
     Ad
    1.07
     ad
    1.05
     valorem
    0.99
     Hoc
    0.94
    jective
    0.93
    Ad
    0.93
     nause
    0.89
    mittedly
    0.85
    Act Density 0.045%

    No Known Activations