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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的眼睛
    -0.08
    .setDate
    -0.07
    睇
    -0.07
    enez
    -0.07
    enie
    -0.07
    works
    -0.07
    exam
    -0.07
    _fx
    -0.06
    Shock
    -0.06
    refix
    -0.06
    POSITIVE LOGITS
     Literal
    0.07
    .setProperty
    0.07
    临沂
    0.07
     BBB
    0.06
    促成
    0.06
    潍坊
    0.06
    הר
    0.06
     predominant
    0.06
     CAST
    0.06
     seller
    0.06
    Act Density 0.048%

    No Known Activations