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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ENABLE
    -0.07
     knob
    -0.06
    (click
    -0.06
    judge
    -0.06
     VIC
    -0.06
    _my
    -0.06
    topics
    -0.06
    话
    -0.06
    _vector
    -0.06
     Convenient
    -0.06
    POSITIVE LOGITS
     Immediately
    0.07
    บร
    0.06
    ी-
    0.06
    υ
    0.06
     خداوند
    0.06
     ctx
    0.06
    тра
    0.06
     Sofa
    0.06
    (stdout
    0.06
     XPAR
    0.06
    Act Density 0.001%

    No Known Activations