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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    保健
    -0.07
    Rio
    -0.07
    贯通
    -0.07
     grants
    -0.07
    砮
    -0.07
     prise
    -0.06
    (lines
    -0.06
     roadmap
    -0.06
     belt
    -0.06
    Pago
    -0.06
    POSITIVE LOGITS
    Fil
    0.07
     Spo
    0.07
    .comments
    0.07
     asymmetric
    0.07
     JJ
    0.06
    .volley
    0.06
     Oliveira
    0.06
    的情绪
    0.06
    发财
    0.06
     красот
    0.06
    Act Density 0.002%

    No Known Activations