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

    Neuronpedia

    INDEX
    Explanations

    international

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -module
    -0.08
     entrepreneur
    -0.08
    .ReLU
    -0.07
    (setq
    -0.07
     Ud
    -0.07
    ];↵
    -0.06
     reviewed
    -0.06
    常德
    -0.06
     Charts
    -0.06
    :test
    -0.06
    POSITIVE LOGITS
    wives
    0.07
    orna
    0.07
     steals
    0.07
    inos
    0.07
     SNAP
    0.07
    inging
    0.07
    ific
    0.07
    банк
    0.07
     Petty
    0.07
     Swim
    0.06
    Act Density 0.224%

    No Known Activations