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

    Neuronpedia

    INDEX
    Explanations

    Opening parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ダイ
    -0.07
     STEM
    -0.06
     perish
    -0.06
    idth
    -0.06
     fridge
    -0.06
    patches
    -0.06
    طار
    -0.06
    ecer
    -0.06
     Mesh
    -0.06
     WI
    -0.06
    POSITIVE LOGITS
    ी.
    0.06
    __(↵
    0.06
     divers
    0.06
    ैं.↵
    0.06
    ।
    0.06
    prevent
    0.06
    _GREEN
    0.06
    .shutdown
    0.06
    ();↵↵
    0.06
    .loggedIn
    0.06
    Act Density 0.004%

    No Known Activations