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

    Neuronpedia

    INDEX
    Explanations

    competitive analysis and discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्करी
    0.54
    চ্ছুক
    0.51
    PLAC
    0.50
     እነዚህ
    0.50
    Asc
    0.50
    Dealing
    0.49
    Vai
    0.49
    GOING
    0.49
    मो
    0.49
    SOs
    0.49
    POSITIVE LOGITS
     with
    0.51
     def
    0.47
     detect
    0.47
     et
    0.47
     de
    0.46
    ów
    0.45
    um
    0.45
     model
    0.43
    owska
    0.42
     Analyst
    0.41
    Act Density 0.001%

    No Known Activations