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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zijn
    -0.07
    ابه
    -0.06
     Dialogue
    -0.06
     отправ
    -0.06
    otřeb
    -0.06
    _mb
    -0.06
    /Core
    -0.06
    Ban
    -0.06
    �
    -0.06
     bonding
    -0.06
    POSITIVE LOGITS
    .authorization
    0.06
    /';↵
    0.06
    .heroku
    0.06
    经济
    0.06
    .]↵↵
    0.06
     Background
    0.06
    -plugin
    0.06
     Mitsubishi
    0.06
     Marlins
    0.06
     Cowboy
    0.06
    Act Density 0.000%

    No Known Activations