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

    Neuronpedia

    INDEX
    Explanations

    IP

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aniyati
    0.58
    boiler
    0.57
     ಚುನಾವಣ
    0.56
    ⓪
    0.56
    lac
    0.55
    xlabel
    0.55
    Fon
    0.55
    MakeRange
    0.55
     manifestó
    0.55
    lace
    0.54
    POSITIVE LOGITS
     inter
    0.58
     oops
    0.58
     SEE
    0.57
     loves
    0.56
     Else
    0.56
     iaa
    0.56
     else
    0.54
     Oops
    0.54
     interl
    0.54
     ELSE
    0.53
    Act Density 0.001%

    No Known Activations