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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.40
     It
    0.38
     Information
    0.34
     I
    0.33
     A
    0.33
     And
    0.32
     If
    0.32
    lty
    0.30
    lng
    0.30
    worthiness
    0.29
    POSITIVE LOGITS
     in
    0.50
    は
    0.47
    在
    0.45
     eiusmod
    0.42
     في
    0.41
    ન
    0.38
     σε
    0.38
    ও
    0.38
    ۔
    0.38
    ق
    0.38
    Act Density 0.431%

    No Known Activations