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

    Neuronpedia

    INDEX
    Explanations

    describing concepts or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     എം
    0.54
    óln
    0.50
     تأثير
    0.48
    iophor
    0.47
     言っ
    0.47
    跖
    0.47
    ენი
    0.45
    autor
    0.45
    neu
    0.44
     Neues
    0.44
    POSITIVE LOGITS
    S
    0.56
     B
    0.53
     P
    0.49
    m
    0.48
     requests
    0.48
     Bean
    0.48
     Requests
    0.48
     Amenities
    0.47
    P
    0.47
     Reasonable
    0.47
    Act Density 0.001%

    No Known Activations