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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     starts
    -0.08
     medicine
    -0.07
     бес
    -0.07
     Exception
    -0.07
     full
    -0.07
    eta
    -0.07
     pills
    -0.06
    /List
    -0.06
    正
    -0.06
     Device
    -0.06
    POSITIVE LOGITS
    .textContent
    0.07
    语
    0.07
    alleries
    0.06
     flies
    0.06
     setIs
    0.06
     helicopt
    0.06
    thritis
    0.06
     Prepared
    0.06
    brahim
    0.06
     Daten
    0.06
    Act Density 0.621%

    No Known Activations