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

    Neuronpedia

    INDEX
    Explanations

    R&D

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -end
    -0.07
    นำ
    -0.07
     earnest
    -0.07
    .us
    -0.06
    cn
    -0.06
     Dan
    -0.06
    /
    -0.06
     подс
    -0.06
    _builder
    -0.06
     tire
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////↵
    0.06
    ('/')↵
    0.06
    证券
    0.06
     〜
    0.06
     staunch
    0.06
     Mosque
    0.06
     Ariel
    0.06
     shade
    0.06
    Focused
    0.06
    InstanceState
    0.06
    Act Density 0.025%

    No Known Activations