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

    Neuronpedia

    INDEX
    Explanations

    href

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =url
    -0.07
    😒
    -0.07
    升温
    -0.07
    像是
    -0.07
     wild
    -0.07
    🧡
    -0.07
    .cards
    -0.07
     wf
    -0.06
     possui
    -0.06
     ogs
    -0.06
    POSITIVE LOGITS
    Published
    0.07
     Perception
    0.07
    تماع
    0.07
    jay
    0.07
    健康
    0.07
    เทคโนโลย
    0.07
    家门口
    0.07
     announced
    0.07
    (CType
    0.06
    Civil
    0.06
    Act Density 0.000%

    No Known Activations