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

    Neuronpedia

    INDEX
    Explanations

    start of new sentences or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multiplicative
    0.38
     mollus
    0.37
     logits
    0.37
     dilution
    0.36
     violência
    0.36
    疃
    0.36
     hadron
    0.36
     sparsity
    0.35
     carbonyl
    0.35
     metac
    0.35
    POSITIVE LOGITS
    eny
    0.44
    iti
    0.44
    olic
    0.44
    ulaire
    0.41
    ela
    0.40
    way
    0.40
    ru
    0.40
    ue
    0.39
     Award
    0.39
    archive
    0.39
    Act Density 0.000%

    No Known Activations