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

    Neuronpedia

    INDEX
    Explanations

    as a part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ENCE
    0.22
    ちなみに
    0.21
    rence
    0.21
    状況
    0.20
    RENCE
    0.20
    schluss
    0.20
    IZATION
    0.19
    ைச்
    0.19
    いっぱい
    0.19
    имо
    0.19
    POSITIVE LOGITS
     součást
    0.27
     onderdeel
    0.27
     houseplants
    0.26
     a
    0.25
     standalone
    0.24
     part
    0.24
     transplants
    0.23
    一名
    0.23
     orphans
    0.23
     beneficiaries
    0.23
    Act Density 0.078%

    No Known Activations