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

    Neuronpedia

    INDEX
    Explanations

    tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cay
    -0.07
     ninete
    -0.07
    燮
    -0.07
    قتر
    -0.06
    交代
    -0.06
    _);
↵
    -0.06
    ountain
    -0.06
     Overse
    -0.06
    ')+
    -0.06
    如果不是
    -0.06
    POSITIVE LOGITS
    _job
    0.08
     רבים
    0.07
     Owl
    0.07
    릭
    0.07
     sibling
    0.07
     popularity
    0.06
     długo
    0.06
    izational
    0.06
     oben
    0.06
     genotype
    0.06
    Act Density 0.002%

    No Known Activations