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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AE
    -0.06
     всего
    -0.06
    olarity
    -0.06
    症
    -0.06
    _validate
    -0.06
     expertise
    -0.06
     mating
    -0.06
    's
    -0.06
    ’s
    -0.06
    键
    -0.06
    POSITIVE LOGITS
     imperson
    0.07
    __;↵
    0.07
     sağlamak
    0.07
     
    0.06
     stojí
    0.06
     �
    0.06
     HI
    0.06
    %H
    0.06
     دانشجوی
    0.06
     آلمان
    0.06
    Act Density 0.033%

    No Known Activations