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

    Neuronpedia

    INDEX
    Explanations

    course, however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ités
    0.41
     wineries
    0.38
     resorts
    0.37
     stesse
    0.35
    ই
    0.35
    忥
    0.34
     aides
    0.34
     adversaries
    0.34
     visites
    0.34
     contours
    0.34
    POSITIVE LOGITS
    的
    0.40
    J
    0.35
    의
    0.34
    n
    0.34
    の
    0.34
     mesela
    0.34
     Misalnya
    0.33
     Hinweis
    0.33
     R
    0.32
    ता
    0.32
    Act Density 0.228%

    No Known Activations