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

    Neuronpedia

    INDEX
    Explanations

    code, units, and government

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মোল
    0.39
    ិន
    0.38
    的话
    0.38
    λί
    0.37
    ኚ
    0.37
    বরা
    0.36
    ܝܢ
    0.35
     $*$-
    0.35
     वग
    0.34
    Ϲ
    0.34
    POSITIVE LOGITS
     PAC
    0.43
     उदा
    0.42
     PA
    0.41
     tetra
    0.40
     pousse
    0.40
    ohex
    0.40
    PIA
    0.38
    pires
    0.38
     kor
    0.38
    WIRE
    0.38
    Act Density 0.000%

    No Known Activations