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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fee
    -0.08
     More
    -0.08
     Their
    -0.07
     vscode
    -0.07
     sor
    -0.07
     their
    -0.07
    istributions
    -0.07
     nonce
    -0.07
     För
    -0.07
    .ActionListener
    -0.06
    POSITIVE LOGITS
     мы
    0.07
     Мы
    0.07
    倒
    0.07
     hereby
    0.07
     us
    0.07
     I
    0.07
     we
    0.06
    派
    0.06
     ya
    0.06
     я
    0.06
    Act Density 0.054%

    No Known Activations