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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owane
    -0.07
    bench
    -0.07
    pref
    -0.06
     νο
    -0.06
    اعر
    -0.06
    ')}}"
    -0.06
    college
    -0.06
    殖
    -0.06
    áze
    -0.06
    871
    -0.06
    POSITIVE LOGITS
    .win
    0.06
    .kotlin
    0.06
     společnost
    0.06
    (deg
    0.06
     규
    0.06
     redesigned
    0.06
    ervention
    0.06
     firstName
    0.06
    /(
    0.06
    дая
    0.06
    Act Density 0.000%

    No Known Activations