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

    Neuronpedia

    INDEX
    Explanations

    asking for context or clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    2.22
     और
    2.00
     এবং
    1.98
     आणि
    1.94
     ਅਤੇ
    1.92
    和
    1.90
     và
    1.88
     અને
    1.84
     и
    1.83
    และ
    1.80
    POSITIVE LOGITS
    ,
    1.30
    ,...
    1.26
    ،
    1.24
    ,..
    1.19
    ).
    1.16
    ）。
    1.16
    ].
    1.15
    。
    1.13
    ").
    1.12
    ,…
    1.12
    Act Density 0.453%

    No Known Activations