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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “In
    -0.07
     números
    -0.06
    ”—
    -0.06
    peon
    -0.06
     وارد
    -0.06
    謝
    -0.06
     urn
    -0.06
    ��
    -0.06
     nao
    -0.06
    Det
    -0.06
    POSITIVE LOGITS
    lığına
    0.07
     γλώ
    0.07
     çek
    0.07
    .Fatalf
    0.06
     prematurely
    0.06
    梨
    0.06
    怎
    0.06
    ubl
    0.06
    σμα
    0.06
    (Blueprint
    0.06
    Act Density 0.004%

    No Known Activations