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

    Neuronpedia

    INDEX
    Explanations

    website titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Import
    0.42
    ждён
    0.37
    Where
    0.36
    ίδ
    0.36
    جہاں
    0.36
    韫
    0.34
    პი
    0.34
    本事
    0.34
    Improvements
    0.33
     confronted
    0.33
    POSITIVE LOGITS
     crepe
    0.35
    levation
    0.35
     Prince
    0.34
     principe
    0.34
     Sir
    0.33
    onation
    0.33
    cyber
    0.33
     musica
    0.33
    Prince
    0.32
     пое
    0.32
    Act Density 0.003%

    No Known Activations