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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sue
    -0.07
     Оч
    -0.07
    ลงทะเบ
    -0.06
     Dominic
    -0.06
     Bubble
    -0.06
    \:
    -0.06
    不可或
    -0.06
     nadzie
    -0.06
     Müslü
    -0.06
     scrut
    -0.06
    POSITIVE LOGITS
    ":"'
    0.08
    ็น
    0.08
    voir
    0.07
     roofing
    0.07
    ourd
    0.06
    审美
    0.06
     voir
    0.06
     Renderer
    0.06
     poi
    0.06
     mileage
    0.06
    Act Density 0.044%

    No Known Activations