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

    Neuronpedia

    INDEX
    Explanations

    programming variables and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moistened
    0.18
     शिम
    0.18
    परेटर
    0.18
    ುವ
    0.18
    雍
    0.17
    위원회
    0.17
    ​]]
    0.17
    fibr
    0.17
    icana
    0.17
    soaked
    0.17
    POSITIVE LOGITS
     ==
    0.19
     !=
    0.18
    );
    0.18
    !=
    0.17
     verlie
    0.16
     //
    0.16
     %
    0.16
    ==
    0.16
     );
    0.15
     Which
    0.15
    Act Density 0.229%

    No Known Activations