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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    融资
    -0.09
     அரசு
    -0.08
    ့်
    -0.08
    რი
    -0.08
    _export
    -0.08
     Export
    -0.08
     Daytona
    -0.08
     processo
    -0.08
     정부
    -0.08
     Curriculum
    -0.08
    POSITIVE LOGITS
     greeting
    0.14
    返信
    0.13
     greet
    0.13
     greetings
    0.12
     reply
    0.12
     personable
    0.12
    回应
    0.12
    回复
    0.12
    Greeting
    0.12
    .reply
    0.11
    Act Density 0.102%

    No Known Activations