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

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Quotes
    -0.08
     Im
    -0.07
    مواطن
    -0.07
    without
    -0.06
     Identified
    -0.06
     editable
    -0.06
     And
    -0.06
     up
    -0.06
    .sb
    -0.06
    MIC
    -0.06
    POSITIVE LOGITS
    etical
    0.07
     ella
    0.07
    yme
    0.07
    🧠
    0.07
    _producto
    0.07
    】,【
    0.07
     EGL
    0.07
    mania
    0.07
    🐟
    0.07
    (eventName
    0.07
    Act Density 0.105%

    No Known Activations