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

    Neuronpedia

    INDEX
    Explanations

    probability and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     êtes
    0.86
    everyone
    0.86
    仪式
    0.86
     aerospace
    0.82
    走
    0.82
     améliorer
    0.82
     ideologies
    0.81
     allemande
    0.80
     legacy
    0.80
     everyone
    0.80
    POSITIVE LOGITS
    следова
    0.88
     Probably
    0.84
     אבל
    0.84
     Probability
    0.82
    Concerning
    0.82
     kemungkinan
    0.77
    probable
    0.75
     wahrscheinlich
    0.75
     Concerning
    0.74
    следование
    0.74
    Act Density 0.001%

    No Known Activations