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

    Neuronpedia

    INDEX
    Explanations

    offers to continue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recently
    0.70
     particular
    0.70
     genel
    0.69
     בשנת
    0.68
     recent
    0.67
     offerings
    0.66
     হলেও
    0.65
     alliances
    0.65
     permita
    0.65
     ehemalige
    0.65
    POSITIVE LOGITS
     Done
    1.54
     Voilà
    1.51
    Voilà
    1.47
    Done
    1.46
    Yep
    1.36
     voila
    1.35
     Yep
    1.34
     Yup
    1.30
     Boom
    1.28
     Vo
    1.28
    Act Density 0.441%

    No Known Activations