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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IOR
    -0.07
     dear
    -0.07
    VERBOSE
    -0.07
    -viol
    -0.07
    CreatedBy
    -0.07
    🤝
    -0.07
     smelled
    -0.07
    ior
    -0.06
    🍫
    -0.06
    _rewards
    -0.06
    POSITIVE LOGITS
    writers
    0.07
     البع
    0.07
    _manager
    0.07
     husbands
    0.07
     conventions
    0.07
     backing
    0.07
    Cargo
    0.06
    收缩
    0.06
    мин
    0.06
    高峰期
    0.06
    Act Density 0.001%

    No Known Activations