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

    Neuronpedia

    INDEX
    Explanations

    Offering assistance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ꮑ
    -0.07
     Brace
    -0.07
    谍
    -0.07
    [id
    -0.07
    这个词
    -0.06
     Arrest
    -0.06
     organizational
    -0.06
     Cyr
    -0.06
     valueType
    -0.06
     Kirst
    -0.06
    POSITIVE LOGITS
     █████
    0.07
    held
    0.07
    allas
    0.07
    ,total
    0.07
    手中
    0.07
    help
    0.06
    äl
    0.06
    넉
    0.06
    手指
    0.06
    折
    0.06
    Act Density 0.043%

    No Known Activations