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

    Neuronpedia

    INDEX
    Explanations

    historical figures' names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atherine
    0.36
    ZC
    0.35
    Mi
    0.34
    familyName
    0.34
    Juan
    0.34
    June
    0.33
    Cidade
    0.32
    UNC
    0.32
     Joanna
    0.32
    REQ
    0.31
    POSITIVE LOGITS
     plass
    0.34
     filter
    0.33
     filters
    0.32
     compressed
    0.31
     peripherals
    0.30
     emphasize
    0.30
     veil
    0.30
     jellyfish
    0.30
    你
    0.30
     জায়
    0.29
    Act Density 0.006%

    No Known Activations