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

    Neuronpedia

    INDEX
    Explanations

    Digit of a number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     makin
    -0.07
    うち
    -0.06
    etr
    -0.06
     Covers
    -0.06
    mur
    -0.06
    ุก
    -0.06
    „ظ
    -0.06
    ुक
    -0.06
    る
    -0.06
     NUIT
    -0.06
    POSITIVE LOGITS
     ABC
    0.06
     SignUp
    0.06
     hormones
    0.06
    :params
    0.06
    Window
    0.06
    male
    0.06
    征
    0.06
     объек
    0.06
     ""))↵
    0.06
     birden
    0.06
    Act Density 0.009%

    No Known Activations