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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Africa
    -0.07
    MSG
    -0.06
    ग
    -0.06
    selectAll
    -0.06
     rootReducer
    -0.06
    uite
    -0.06
    selector
    -0.06
    ра
    -0.06
     ba
    -0.06
    ags
    -0.06
    POSITIVE LOGITS
    ]))
    0.08
    /',
    0.07
    므로
    0.07
    隠
    0.07
    ,’”
    0.07
    )_
    0.07
    )));
    0.07
    ']]
    0.07
     ΠΑΝ
    0.07
    )).
    0.06
    Act Density 0.002%

    No Known Activations