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

    Neuronpedia

    INDEX
    Explanations

    numbers ending in 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chal
    0.43
    ＰＥ
    0.41
     auster
    0.40
    Chal
    0.40
    რულ
    0.40
    audioType
    0.38
    мера
    0.37
     attest
    0.37
     川
    0.36
     supplementing
    0.36
    POSITIVE LOGITS
    fac
    0.39
     MM
    0.39
    CodeAttribute
    0.38
     cellule
    0.37
    斓
    0.36
    লিত
    0.36
     cell
    0.35
     patented
    0.35
    แรม
    0.35
    fier
    0.35
    Act Density 0.001%

    No Known Activations