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

    Neuronpedia

    INDEX
    Explanations

    modular arithmetic and number theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Plast
    0.45
     प्लास्टिक
    0.44
    痱
    0.44
    LuaPush
    0.40
    ハリ
    0.39
     પોલી
    0.39
    ⛱
    0.38
    াঙ্গীর
    0.38
     필
    0.38
    Therates
    0.38
    POSITIVE LOGITS
    Modular
    0.65
     modular
    0.64
     Modular
    0.62
    modular
    0.57
     arithmetic
    0.54
    Arithmetic
    0.54
     elliptic
    0.46
     Arithmetic
    0.44
     autom
    0.43
     aritmética
    0.42
    Act Density 0.005%

    No Known Activations