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

    Neuronpedia

    INDEX
    Explanations

    compensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wear
    -0.07
    -Compatible
    -0.07
     vacuum
    -0.06
    -disabled
    -0.06
    ']);
↵
    -0.06
     sap
    -0.06
     folks
    -0.06
    Lots
    -0.06
    ，对
    -0.06
    ()))
↵
    -0.06
    POSITIVE LOGITS
     asoci
    0.07
    _ov
    0.06
    /UI
    0.06
     outras
    0.06
    inars
    0.06
    atively
    0.06
     PSI
    0.06
    ："
    0.05
     Judith
    0.05
    Tuesday
    0.05
    Act Density 0.091%

    No Known Activations