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

    Neuronpedia

    INDEX
    Explanations

    random numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आंव
    0.40
     المدر
    0.39
    ுமா
    0.37
     Mantel
    0.37
    聡
    0.37
    ClrBit
    0.36
    kunde
    0.36
    芷
    0.36
    CrL
    0.35
    ngr
    0.35
    POSITIVE LOGITS
     admite
    0.40
     choisissez
    0.38
    isinde
    0.38
     seeks
    0.37
    দানে
    0.36
    衤
    0.36
     ఒ
    0.36
     recommends
    0.36
    डले
    0.36
     Kidd
    0.35
    Act Density 0.000%

    No Known Activations