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

    Neuronpedia

    INDEX
    Explanations

    want/like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    India
    -0.08
    Astr
    -0.07
     temática
    -0.07
    Ngu
    -0.07
     complemented
    -0.07
    Federal
    -0.07
    یے
    -0.07
     Bharat
    -0.07
    ερ
    -0.07
     aviation
    -0.07
    POSITIVE LOGITS
     shuffle
    0.10
     emerge
    0.09
     iterate
    0.08
     อย
    0.08
    shuffle
    0.08
     эксперимент
    0.08
     regain
    0.08
     cherish
    0.08
     şa
    0.08
     gə
    0.08
    Act Density 0.001%

    No Known Activations