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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     חו
    -0.07
    知識
    -0.07
    ĝ
    -0.07
     Dew
    -0.06
     describes
    -0.06
    Pref
    -0.06
    ,"
    -0.06
    朴素
    -0.06
     BuzzFeed
    -0.06
     작업
    -0.06
    POSITIVE LOGITS
     bod
    0.08
    出来る
    0.07
    -purpose
    0.07
     scram
    0.07
     apar
    0.07
    Uid
    0.07
    modal
    0.07
    meth
    0.07
    大多是
    0.07
    Isl
    0.06
    Act Density 0.025%

    No Known Activations