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

    Neuronpedia

    INDEX
    Explanations

    quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     circa
    -0.07
    packing
    -0.07
    etro
    -0.07
    rips
    -0.07
    랩
    -0.06
    חק
    -0.06
    _templates
    -0.06
    enarios
    -0.06
     pracy
    -0.06
    orgeous
    -0.06
    POSITIVE LOGITS
    -chevron
    0.09
    acles
    0.07
    (bar
    0.07
    ユーザ
    0.07
    我去
    0.07
    ⛸
    0.07
     Alien
    0.07
     *)[
    0.06
    üssen
    0.06
     ян
    0.06
    Act Density 0.092%

    No Known Activations