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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skyrocket
    -0.07
    .decoder
    -0.07
    َم
    -0.07
    uire
    -0.06
    <_
    -0.06
    HttpException
    -0.06
     PLAN
    -0.06
    르게
    -0.06
    eren
    -0.06
     एज
    -0.06
    POSITIVE LOGITS
     cena
    0.08
    ため
    0.07
    ací
    0.07
     alimentos
    0.07
     aids
    0.07
     acción
    0.06
    riendly
    0.06
    esser
    0.06
    >/
    0.06
    ปก
    0.06
    Act Density 0.035%

    No Known Activations