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

    Neuronpedia

    INDEX
    Explanations

    starting something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     superposition
    1.00
     semblable
    0.95
     juxtaposition
    0.95
     attributable
    0.93
     bystand
    0.90
    INVISIBLE
    0.90
     closer
    0.90
     mobs
    0.89
     togetherness
    0.89
    接觸
    0.88
    POSITIVE LOGITS
     dataset
    1.08
     утвер
    1.06
     desej
    1.01
     Dataset
    1.01
     النموذج
    1.00
     opções
    0.99
    が必要です
    0.97
     desired
    0.95
    desired
    0.94
    filename
    0.94
    Act Density 0.170%

    No Known Activations