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

    Neuronpedia

    INDEX
    Explanations

    vulnerable sharing and well wishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    0.80
    _
    0.60
     మరియు
    0.59
     וא
    0.55
    /
    0.55
    ،
    0.55
    त
    0.53
     및
    0.52
    కు
    0.50
    т
    0.49
    POSITIVE LOGITS
    ２
    0.57
     JFK
    0.54
     Masai
    0.54
     itu
    0.54
     soooo
    0.54
    ３
    0.54
     JIS
    0.53
     JEE
    0.52
    java
    0.52
    navbarSupported
    0.52
    Act Density 0.168%

    No Known Activations