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

    Neuronpedia

    INDEX
    Explanations

    natural writing style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .setSize
    -0.07
     Sammy
    -0.07
    gne
    -0.07
     getClass
    -0.07
     government
    -0.07
    langle
    -0.07
    /get
    -0.06
    \Table
    -0.06
    _specific
    -0.06
    gef
    -0.06
    POSITIVE LOGITS
     actress
    0.07
    姨
    0.07
     Realm
    0.07
     lý
    0.07
     özelli
    0.07
     relocate
    0.07
     added
    0.06
    FILTER
    0.06
     alien
    0.06
     priced
    0.06
    Act Density 0.042%

    No Known Activations