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

    Neuronpedia

    INDEX
    Explanations

    parts of names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PROPERTIES
    0.41
     Fähigkeiten
    0.41
     propriétés
    0.39
     često
    0.38
     CustB
    0.38
     ganske
    0.38
     Rxc
    0.38
    ണാ
    0.37
     Anspr
    0.37
     procédures
    0.37
    POSITIVE LOGITS
    udos
    0.41
     Nigeria
    0.41
    op
    0.38
     northern
    0.38
    晾
    0.38
    ived
    0.37
     York
    0.37
    urium
    0.36
    ol
    0.36
     Ireland
    0.36
    Act Density 0.001%

    No Known Activations