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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insurance
    -0.07
    素
    -0.07
     gens
    -0.07
     "{{
    -0.07
    ~/
    -0.06
    /.
    -0.06
    _tmp
    -0.06
    roduced
    -0.06
    DIS
    -0.06
     teenagers
    -0.06
    POSITIVE LOGITS
    gorit
    0.08
    景象
    0.07
    clide
    0.07
     يقول
    0.07
    쪼
    0.07
     overwrite
    0.07
    olders
    0.07
    UBLIC
    0.07
    cimiento
    0.07
     Vimeo
    0.07
    Act Density 0.011%

    No Known Activations