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

    Neuronpedia

    INDEX
    Explanations

    describing negative states of characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     astounding
    0.99
    withstanding
    0.98
     včetně
    0.95
    oretical
    0.95
     vyd
    0.95
     название
    0.94
     Herstellung
    0.93
     unbelievable
    0.93
     př
    0.92
     opet
    0.92
    POSITIVE LOGITS
    glers
    1.16
     chefs
    0.99
    lers
    0.98
     chef
    0.96
     households
    0.96
    ному
    0.91
     peasants
    0.91
    läger
    0.90
    heden
    0.90
    IANS
    0.89
    Act Density 0.197%

    No Known Activations