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

    Neuronpedia

    INDEX
    Explanations

    provider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phen
    0.26
     fenomen
    0.25
     thereof
    0.24
     gamepad
    0.23
    ोप
    0.23
     সন
    0.22
     контро
    0.22
    phen
    0.22
    Magn
    0.22
     прод
    0.22
    POSITIVE LOGITS
     Obviously
    0.26
     Actually
    0.25
     Admittedly
    0.25
     Definitely
    0.25
    俗
    0.24
     Judging
    0.24
    繊維
    0.24
     oms
    0.23
     suger
    0.23
    éli
    0.23
    Act Density 0.005%

    No Known Activations