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

    Neuronpedia

    INDEX
    Explanations

    Russian words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مر
    -0.07
     DO
    -0.07
     CARD
    -0.07
     Psychological
    -0.07
     recognized
    -0.07
    .GridView
    -0.06
     플
    -0.06
     carrier
    -0.06
    เคล
    -0.06
     Thomas
    -0.06
    POSITIVE LOGITS
    nze
    0.07
    _ram
    0.06
     začátku
    0.06
     중앙
    0.06
    .removeListener
    0.06
    NSMutableDictionary
    0.06
    isbury
    0.06
     Salisbury
    0.06
    Refer
    0.06
    .toolStripButton
    0.06
    Act Density 0.016%

    No Known Activations