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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RV
    -0.07
    Hide
    -0.07
     hud
    -0.06
     rit
    -0.06
    杀
    -0.06
    اج
    -0.06
    \Api
    -0.06
     داده
    -0.06
     추
    -0.06
     administer
    -0.06
    POSITIVE LOGITS
    'LBL
    0.07
    -,
    0.06
    mlx
    0.06
    PR
    0.06
     Pokud
    0.06
    (dec
    0.06
     strained
    0.06
     +:+
    0.06
    °N
    0.06
    ockey
    0.06
    Act Density 0.078%

    No Known Activations