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

    Neuronpedia

    INDEX
    Explanations

    Number sequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PVC
    -0.08
    _PIN
    -0.07
     comport
    -0.07
    ptype
    -0.07
    وية
    -0.07
     consume
    -0.07
    Cd
    -0.07
     hardwood
    -0.06
     Password
    -0.06
    ストレス
    -0.06
    POSITIVE LOGITS
     была
    0.07
     Megan
    0.07
     Stacy
    0.07
     reveal
    0.07
     него
    0.07
    阐明
    0.06
     resorts
    0.06
     surprised
    0.06
     Alternate
    0.06
     demo
    0.06
    Act Density 0.016%

    No Known Activations