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

    Neuronpedia

    INDEX
    Explanations

    anecd

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vastly
    -0.07
    465
    -0.06
     Burger
    -0.06
    (cube
    -0.06
    505
    -0.06
    ToMany
    -0.06
     بها
    -0.06
    370
    -0.06
    .stock
    -0.06
    _large
    -0.06
    POSITIVE LOGITS
     listening
    0.07
    �
    0.07
     Tip
    0.07
    かい
    0.07
    ippy
    0.07
    atch
    0.07
    摄
    0.07
    탕
    0.06
    ♪
    0.06
     dejar
    0.06
    Act Density 0.002%

    No Known Activations