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

    Neuronpedia

    INDEX
    Explanations

    subjects and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    các
    0.70
    วัสดี
    0.66
    ূন
    0.65
    ಥವಾ
    0.65
     elettronica
    0.64
    //////////
    0.64
    ///////////////
    0.63
    大量的
    0.62
     );//
    0.62
     cosidd
    0.62
    POSITIVE LOGITS
    ?
    0.60
    ating
    0.55
    ates
    0.47
    '
    0.45
    ens
    0.45
    ize
    0.45
    iah
    0.45
    .
    0.44
    ​​
    0.44
    op
    0.42
    Act Density 0.009%

    No Known Activations