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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clusive
    -0.08
    ourke
    -0.08
    .generate
    -0.07
    -handed
    -0.07
    essment
    -0.07
     sunscreen
    -0.07
     Pedro
    -0.07
    通行证
    -0.07
    氢能
    -0.07
    oes
    -0.07
    POSITIVE LOGITS
    姚
    0.06
    arrêt
    0.06
     gusto
    0.06
     obl
    0.06
    벗
    0.06
    _exact
    0.06
     Americas
    0.06
    垕
    0.06
     Alle
    0.06
    閱
    0.06
    Act Density 0.465%

    No Known Activations