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

    Neuronpedia

    INDEX
    Explanations

    cannot access links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    padded
    0.39
    ထိ
    0.38
    诨
    0.36
    本地
    0.36
     Rabbi
    0.36
     serif
    0.35
    cse
    0.35
    ACING
    0.35
    chende
    0.35
    raphic
    0.35
    POSITIVE LOGITS
     आकर्
    0.43
    According
    0.41
     rings
    0.40
    unità
    0.39
    ตาม
    0.37
     karne
    0.37
     according
    0.36
    Dreams
    0.36
     attra
    0.36
     zv
    0.36
    Act Density 0.000%

    No Known Activations