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

    Neuronpedia

    INDEX
    Explanations

    legal and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     어
    -0.07
     Ember
    -0.07
    .IsSuccess
    -0.07
    𝕿
    -0.06
    Instance
    -0.06
    从小
    -0.06
     לל
    -0.06
    عجز
    -0.06
    แ
    -0.06
    还不
    -0.06
    POSITIVE LOGITS
     Growth
    0.07
    므로
    0.07
    גוב
    0.07
    _hero
    0.07
    essay
    0.07
    cab
    0.07
     группы
    0.07
    文档
    0.07
    🤳
    0.06
    orias
    0.06
    Act Density 0.004%

    No Known Activations