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

    Neuronpedia

    INDEX
    Explanations

    get/gets + state/change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    2.42
    ają
    2.14
    ]))
    2.13
    obr
    2.08
    oł
    2.05
    ls
    2.04
    ])));
    2.00
    lb
    2.00
    ſelf
    1.98
    sto
    1.97
    POSITIVE LOGITS
    चलिए
    2.04
     renewal
    2.01
     pleasantly
    2.00
     revolved
    2.00
    हमने
    1.98
     অস্থির
    1.97
    करण
    1.96
    henol
    1.92
     faptul
    1.91
     berbah
    1.89
    Act Density 0.034%

    No Known Activations