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

    Neuronpedia

    INDEX
    Explanations

    code formatting or tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acts
    0.43
    <0xC2>
    0.43
     Plugging
    0.38
     Beach
    0.38
     simplifies
    0.37
    ↵
    0.36
     act
    0.36
     Quadr
    0.36
     verko
    0.35
     swift
    0.35
    POSITIVE LOGITS
    ත්වය
    0.44
    NOMBRE
    0.41
    EDED
    0.40
    Gosudarstvennyj
    0.40
    utenção
    0.40
    ಾಣ
    0.40
    BufferedWriter
    0.39
     મહે
    0.39
    ié
    0.39
    急性
    0.39
    Act Density 0.088%

    No Known Activations