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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gam
    -0.07
    	O
    -0.07
     sağlayan
    -0.06
     Elf
    -0.06
    %",
    -0.06
    _endpoint
    -0.06
     compañ
    -0.06
     نظ
    -0.06
    Comp
    -0.06
    ้เก
    -0.06
    POSITIVE LOGITS
    .from
    0.07
    almö
    0.07
     curled
    0.07
     Copenhagen
    0.07
     conception
    0.06
     baptized
    0.06
    rası
    0.06
    δι
    0.06
    .old
    0.06
     Plymouth
    0.06
    Act Density 0.098%

    No Known Activations