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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buyer
    -0.07
    appear
    -0.07
    constant
    -0.07
     theoret
    -0.07
    .UNRELATED
    -0.06
    CLUSIVE
    -0.06
    iren
    -0.06
     description
    -0.06
     Định
    -0.06
    ancing
    -0.06
    POSITIVE LOGITS
     large
    0.08
     Marino
    0.07
     households
    0.07
    _er
    0.07
    rpc
    0.07
    .rx
    0.06
    /se
    0.06
    .simps
    0.06
     MCC
    0.06
    ارهای
    0.06
    Act Density 0.046%

    No Known Activations