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

    Neuronpedia

    INDEX
    Explanations

    form simple sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Express
    0.43
    Compat
    0.38
     Argument
    0.38
     Analyze
    0.37
     Res
    0.37
     Reflection
    0.36
     Tray
    0.35
     пожа
    0.35
    s
    0.35
    Express
    0.35
    POSITIVE LOGITS
     ಕೆಲ
    0.46
    newParameter
    0.44
    𒂗
    0.44
     ಎಂಬ
    0.44
     oftentimes
    0.44
     obligated
    0.43
    辜
    0.43
     overseen
    0.43
     clings
    0.43
     sporadically
    0.43
    Act Density 0.008%

    No Known Activations