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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )x
    -0.07
    _FOREACH
    -0.07
    bars
    -0.06
    IMP
    -0.06
     snippet
    -0.06
     decent
    -0.06
     Roots
    -0.06
    ・ア
    -0.06
     vectors
    -0.06
     фрон
    -0.06
    POSITIVE LOGITS
     مدیر
    0.07
    deniz
    0.07
     passer
    0.07
     threesome
    0.06
    昨
    0.06
    가요
    0.06
     ECS
    0.06
     greeted
    0.06
    .speed
    0.06
    .Update
    0.06
    Act Density 0.016%

    No Known Activations