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

    Neuronpedia

    INDEX
    Explanations

    elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "B
    -0.07
    ighter
    -0.07
     NETWORK
    -0.07
     eight
    -0.07
    North
    -0.07
     North
    -0.07
    форм
    -0.07
    Opening
    -0.07
    Asset
    -0.06
    ाब
    -0.06
    POSITIVE LOGITS
    (Me
    0.07
     contra
    0.07
    u
    0.07
     Cu
    0.06
    男性
    0.06
     i
    0.06
     Ca
    0.06
     <!--<
    0.06
     [|
    0.06
     u
    0.06
    Act Density 0.035%

    No Known Activations