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

    Neuronpedia

    INDEX
    Explanations

    Job descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Costco
    -0.07
     walkers
    -0.06
    Dark
    -0.06
    Vertical
    -0.06
    enade
    -0.06
     websocket
    -0.06
     CVS
    -0.06
     휴
    -0.05
     parser
    -0.05
     Dark
    -0.05
    POSITIVE LOGITS
    .linalg
    0.07
     tailored
    0.07
    กำ
    0.07
    _ASCII
    0.07
    DD
    0.07
    /testify
    0.06
     Tear
    0.06
    SIM
    0.06
    XS
    0.06
     digit
    0.06
    Act Density 0.013%

    No Known Activations