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

    Neuronpedia

    INDEX
    Explanations

    Complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quốc
    -0.06
    _origin
    -0.06
    ่าก
    -0.06
     brightest
    -0.06
     Halk
    -0.06
    large
    -0.06
    [position
    -0.06
     kvinne
    -0.06
     Ones
    -0.06
    without
    -0.06
    POSITIVE LOGITS
     öner
    0.07
    /******/
    0.07
    ificial
    0.07
    itive
    0.06
     (!
    0.06
    ）↵
    0.06
    `↵
    0.06
    atasets
    0.06
    .TIM
    0.06
    �
    0.06
    Act Density 0.224%

    No Known Activations