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

    Neuronpedia

    INDEX
    Explanations

    Bids and proposals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     )↵
    -0.07
     tutors
    -0.07
    PUBLIC
    -0.07
     TForm
    -0.07
     earned
    -0.07
     família
    -0.07
    .Nome
    -0.07
    Patients
    -0.07
     parc
    -0.07
    _don
    -0.06
    POSITIVE LOGITS
    appointed
    0.07
     knees
    0.07
    监督检查
    0.07
    را
    0.07
     amp
    0.07
    깸
    0.07
    まず
    0.06
    plusplus
    0.06
    odynamic
    0.06
    看一下
    0.06
    Act Density 0.016%

    No Known Activations