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

    Neuronpedia

    INDEX
    Explanations

    добав

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    Isl
    -0.07
    ise
    -0.06
     analysed
    -0.06
     若
    -0.06
     valeurs
    -0.06
     struk
    -0.06
    guard
    -0.06
     카지노
    -0.06
    keiten
    -0.06
    POSITIVE LOGITS
     Garlic
    0.08
    .comboBox
    0.07
     loosen
    0.07
     Extra
    0.07
     Cooking
    0.07
    年度
    0.07
     Advent
    0.06
    뷰
    0.06
    έ
    0.06
     درجة
    0.06
    Act Density 0.005%

    No Known Activations