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
    icits
    -0.07
     hå
    -0.07
    Feat
    -0.07
    utz
    -0.07
    inel
    -0.07
    Regs
    -0.07
     matchmaking
    -0.06
    boxes
    -0.06
    radu
    -0.06
    τσι
    -0.06
    POSITIVE LOGITS
    .getService
    0.07
    ">'+↵
    0.07
    주
    0.06
     Україн
    0.06
     Aer
    0.06
    SubMenu
    0.06
    :not
    0.06
     �
    0.06
    )+↵
    0.06
    UpDown
    0.06
    Act Density 0.172%

    No Known Activations