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

    Neuronpedia

    INDEX
    Explanations

    -ring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اير
    -0.06
     faucet
    -0.06
    يت
    -0.06
     आज
    -0.06
    يلا
    -0.06
     کری
    -0.06
     Surf
    -0.06
     glyphs
    -0.06
     своей
    -0.06
    она
    -0.06
    POSITIVE LOGITS
     Number
    0.08
    -number
    0.08
    alarda
    0.07
    (?:
    0.07
    善
    0.07
    asley
    0.06
     설
    0.06
    setEnabled
    0.06
     broth
    0.06
    /order
    0.06
    Act Density 0.001%

    No Known Activations