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

    Neuronpedia

    INDEX
    Explanations

    search query intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cricketer
    0.43
     accountant
    0.40
     মেড
    0.39
     officiel
    0.37
    ьера
    0.37
    ۱۲
    0.37
     कॅ
    0.36
    érieur
    0.36
    argout
    0.36
     collie
    0.36
    POSITIVE LOGITS
    Summar
    0.46
    Triangle
    0.45
    triangle
    0.45
    三角
    0.44
     Triangle
    0.44
     summarise
    0.44
     triangle
    0.42
     Summar
    0.41
     clearly
    0.41
     seemingly
    0.41
    Act Density 0.002%

    No Known Activations