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

    Neuronpedia

    INDEX
    Explanations

    law or distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aku
    0.41
    板
    0.38
    নার
    0.37
    按照
    0.37
     Szcz
    0.37
    Highlight
    0.37
    KAK
    0.36
    нём
    0.35
     Respondent
    0.35
     başlay
    0.34
    POSITIVE LOGITS
     compens
    0.44
     vantagem
    0.43
     drag
    0.43
    φό
    0.42
     estrell
    0.41
     estoque
    0.41
    beer
    0.41
     spese
    0.41
    즙
    0.41
     cuant
    0.40
    Act Density 0.000%

    No Known Activations