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

    Neuronpedia

    INDEX
    Explanations

    ORN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serv
    -0.08
     transporter
    -0.07
    -girl
    -0.07
     warmer
    -0.06
    -part
    -0.06
    AUTH
    -0.06
    ACP
    -0.06
     Sharma
    -0.06
    ์บ
    -0.06
     misrepresented
    -0.06
    POSITIVE LOGITS
     Veteran
    0.06
     mut
    0.06
    ATEGORY
    0.06
    .osgi
    0.06
    اقتص
    0.06
     лю
    0.06
    _DURATION
    0.06
     узн
    0.06
     Occ
    0.06
     spear
    0.06
    Act Density 0.000%

    No Known Activations