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

    Neuronpedia

    INDEX
    Explanations

    ird

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emp
    -0.08
     molds
    -0.07
    sender
    -0.07
    מית
    -0.07
    sensor
    -0.07
    \Entity
    -0.07
    shop
    -0.07
     hãng
    -0.07
    expense
    -0.07
     Sacramento
    -0.07
    POSITIVE LOGITS
    IMITIVE
    0.07
    换句话说
    0.07
    ▚
    0.07
    ));↵↵
    0.07
    fixed
    0.06
    .Completed
    0.06
    镔
    0.06
    .Multiline
    0.06
     Украины
    0.06
    样子
    0.06
    Act Density 0.000%

    No Known Activations