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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lıklar
    -0.07
     dirs
    -0.06
     बल
    -0.06
     serviços
    -0.06
     pagina
    -0.06
    _he
    -0.06
    isos
    -0.06
     vídeos
    -0.06
     zvlá
    -0.06
     cade
    -0.06
    POSITIVE LOGITS
     sleek
    0.08
    货
    0.07
     Modern
    0.07
    .Excel
    0.07
     Breath
    0.07
     synd
    0.07
     Steam
    0.06
     Light
    0.06
    电视
    0.06
     resumed
    0.06
    Act Density 0.025%

    No Known Activations