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

    Neuronpedia

    INDEX
    Explanations

    Strange occurrences happening to people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뚀
    -0.08
    ﱋ
    -0.07
     Lynn
    -0.07
    Team
    -0.07
    깨
    -0.07
    _uv
    -0.07
    głow
    -0.07
    �
    -0.06
    .define
    -0.06
    웁
    -0.06
    POSITIVE LOGITS
     effet
    0.07
     entidad
    0.07
    �
    0.07
    Cont
    0.07
     Exceptions
    0.07
     العراق
    0.06
    =''):↵
    0.06
    宜昌
    0.06
    rections
    0.06
    طقة
    0.06
    Act Density 0.098%

    No Known Activations