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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addChild
    -0.07
    🐕
    -0.07
    ȩ
    -0.07
    跃
    -0.07
    IDD
    -0.07
    .tem
    -0.06
     młodzie
    -0.06
    pine
    -0.06
     Went
    -0.06
     عمل
    -0.06
    POSITIVE LOGITS
     purchasing
    0.08
    Document
    0.07
     stacked
    0.07
     girl
    0.07
     bows
    0.07
     struct
    0.07
     fans
    0.07
     plural
    0.07
     suspects
    0.07
    onga
    0.07
    Act Density 0.002%

    No Known Activations