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

    Neuronpedia

    INDEX
    Explanations

    origin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sWith
    -0.06
    .textContent
    -0.06
    Doug
    -0.06
    ivi
    -0.06
    lh
    -0.06
    uarios
    -0.06
     Panama
    -0.06
    oodoo
    -0.06
    уру
    -0.06
     aşırı
    -0.06
    POSITIVE LOGITS
    weights
    0.07
    @register
    0.06
    complete
    0.06
    VA
    0.06
    BOT
    0.06
    ặ
    0.06
    Fantastic
    0.06
    ้ด
    0.06
    starting
    0.06
     Principle
    0.06
    Act Density 0.019%

    No Known Activations