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

    Neuronpedia

    INDEX
    Explanations

    greentext formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }(
    1.08
    """,
    1.07
    </h2>
    1.01
    すぐに
    1.00
    utiliser
    0.95
    LOC
    0.95
    }/>
    0.94
    Τα
    0.94
    sehen
    0.94
     ‬
    0.93
    POSITIVE LOGITS
    isSelected
    1.14
    osphate
    1.06
     произ
    1.01
    ików
    1.01
    ွေး
    1.00
    muir
    0.96
     thầy
    0.95
     Mauer
    0.95
    ד
    0.94
    ៀប
    0.94
    Act Density 0.002%

    No Known Activations