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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خودرو
    -0.07
     lam
    -0.07
    %\
    -0.07
    .ColumnHeader
    -0.06
     glue
    -0.06
     KeyError
    -0.06
    UserData
    -0.06
     einfach
    -0.06
     excl
    -0.06
     suspension
    -0.06
    POSITIVE LOGITS
     조금
    0.07
    ---------------
    0.07
    нова
    0.07
    �i
    0.07
    -push
    0.06
     possibile
    0.06
    (parcel
    0.06
     shine
    0.06
    anford
    0.06
     -----
    0.06
    Act Density 0.078%

    No Known Activations