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

    Neuronpedia

    INDEX
    Explanations

    simplest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adě
    -0.06
     surrogate
    -0.06
    .parse
    -0.06
     machining
    -0.06
    fixture
    -0.06
    (desc
    -0.06
    ｭ
    -0.06
     Actress
    -0.06
    ]")↵
    -0.06
    dě
    -0.06
    POSITIVE LOGITS
     đúng
    0.07
     расч
    0.07
    _account
    0.07
     cambio
    0.07
     봉
    0.07
     Alexandra
    0.07
     Burb
    0.07
    building
    0.06
     ışık
    0.06
     torrents
    0.06
    Act Density 0.014%

    No Known Activations