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

    Neuronpedia

    INDEX
    Explanations

    vice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    Clusters
    -0.06
    -block
    -0.06
     ​​​
    -0.06
     manifest
    -0.06
    ären
    -0.06
    criptions
    -0.06
    Sarah
    -0.06
     cellar
    -0.06
    _AUTH
    -0.06
    POSITIVE LOGITS
    ώντας
    0.07
     chó
    0.06
     друга
    0.06
    .tele
    0.06
     dudes
    0.06
    heat
    0.06
     Titans
    0.06
    まれ
    0.06
     Oval
    0.06
    ンデ
    0.06
    Act Density 0.003%

    No Known Activations