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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -wheel
    -0.08
    assertEquals
    -0.07
     Global
    -0.07
    Formula
    -0.07
     Basic
    -0.07
     acquisition
    -0.07
     Parents
    -0.07
    Answers
    -0.06
    .connected
    -0.06
    Basic
    -0.06
    POSITIVE LOGITS
    ตน
    0.06
    ur
    0.06
    αρα
    0.06
    oài
    0.06
     Chester
    0.06
     complying
    0.06
    ().'/
    0.06
    :'',
    0.06
     Ori
    0.06
     prohib
    0.05
    Act Density 0.084%

    No Known Activations