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

    Neuronpedia

    INDEX
    Explanations

    shift focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    openweathermap
    2.26
     splashes
    2.12
    लोकन
    2.06
    reuung
    2.03
    })}
    1.99
    RICAL
    1.99
    ご覧
    1.98
     Backbone
    1.95
    )}$.
    1.95
    ebra
    1.92
    POSITIVE LOGITS
    erade
    2.05
    in
    1.98
    ὑ
    1.97
    er
    1.92
    ು
    1.87
    猬
    1.85
     निर्मा
    1.83
    erar
    1.80
     دب
    1.80
    erit
    1.72
    Act Density 0.898%

    No Known Activations