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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arena
    -0.06
    ி
    -0.06
     Amend
    -0.06
     流
    -0.06
     Mish
    -0.06
    ordon
    -0.06
     않는
    -0.06
    吃
    -0.06
    elsius
    -0.06
    ']").
    -0.06
    POSITIVE LOGITS
    /cpu
    0.07
    .MATCH
    0.06
    ΕΤ
    0.06
     DISCLAIMED
    0.06
     İç
    0.06
    abc
    0.06
    ारक
    0.06
    _ini
    0.06
     awk
    0.06
     MYSQL
    0.06
    Act Density 0.051%

    No Known Activations