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

    Neuronpedia

    INDEX
    Explanations

    things against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಬೇ
    0.42
    ન્ટે
    0.38
    anco
    0.33
    portional
    0.32
    र्ट
    0.32
    ből
    0.32
     রই
    0.32
    charCodeAt
    0.32
    それで
    0.31
    いない
    0.31
    POSITIVE LOGITS
     against
    4.78
    against
    4.41
     Against
    4.25
    Against
    4.22
     против
    3.97
     AGAINST
    3.89
     gegen
    3.72
     ضد
    3.58
     tegen
    3.47
     contre
    3.33
    Act Density 0.124%

    No Known Activations