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

    Neuronpedia

    INDEX
    Explanations

    before disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     хорошее
    0.42
     command
    0.42
     elite
    0.40
     good
    0.38
     iyi
    0.38
     infarct
    0.38
     trombone
    0.38
    ەیە
    0.37
     jó
    0.37
     mash
    0.37
    POSITIVE LOGITS
    ніза
    0.45
     contentType
    0.44
    locatorType
    0.43
     Hutchinson
    0.40
    lipped
    0.40
    prnewswire
    0.40
    腈
    0.39
    oglou
    0.39
     způso
    0.38
     ซ
    0.37
    Act Density 0.000%

    No Known Activations