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

    Neuronpedia

    INDEX
    Explanations

    data tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    行动
    -0.07
    .de
    -0.06
     Listen
    -0.06
     tenants
    -0.06
     recorded
    -0.06
     interruption
    -0.06
    	copy
    -0.06
    'user
    -0.06
     Serif
    -0.06
     Cree
    -0.06
    POSITIVE LOGITS
     qs
    0.07
    presence
    0.06
    .GL
    0.06
    坏
    0.06
    _BOOL
    0.06
    ION
    0.06
     wins
    0.06
     Ukrain
    0.06
    .CodeAnalysis
    0.06
    ovně
    0.06
    Act Density 0.012%

    No Known Activations