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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hero
    -0.07
    strong
    -0.06
    .PUT
    -0.06
    کس
    -0.06
     Hand
    -0.06
    -mean
    -0.06
    пон
    -0.06
    alias
    -0.06
    (formData
    -0.06
    voor
    -0.06
    POSITIVE LOGITS
    .|
    0.07
     Aur
    0.06
     امیر
    0.06
     эп
    0.06
    慢
    0.06
    {/
    0.06
     đàn
    0.06
     لل
    0.06
    312
    0.06
    nocení
    0.06
    Act Density 0.049%

    No Known Activations