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

    Neuronpedia

    INDEX
    Explanations

    date format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     añadi
    0.57
     chores
    0.56
    July
    0.55
     jams
    0.52
     envelop
    0.52
     phosphoryl
    0.52
     flyers
    0.52
    carriers
    0.51
     geomet
    0.50
     diversa
    0.50
    POSITIVE LOGITS
     Ми
    0.59
     После
    0.59
     Бре
    0.58
     Ба
    0.57
    ミ
    0.57
     Vaccine
    0.56
    ون
    0.56
     اے
    0.55
     През
    0.55
    مي
    0.54
    Act Density 0.000%

    No Known Activations