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

    Neuronpedia

    INDEX
    Explanations

    Divorce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fellowship
    -0.07
    Pl
    -0.07
    ceeded
    -0.06
    bolt
    -0.06
     symbols
    -0.06
     wood
    -0.06
    safe
    -0.06
    Stan
    -0.06
    Pan
    -0.06
     PACK
    -0.06
    POSITIVE LOGITS
     divorce
    0.11
     divorced
    0.08
     divor
    0.08
    /db
    0.07
    avou
    0.07
     clientes
    0.06
    vine
    0.06
    YPRE
    0.06
    _genre
    0.06
    erç
    0.06
    Act Density 0.002%

    No Known Activations