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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ไฟ
    -0.06
    /MM
    -0.06
     Pai
    -0.06
     xtype
    -0.06
     food
    -0.06
     Baghd
    -0.06
     semiconductor
    -0.06
    하기
    -0.05
    자동
    -0.05
     muff
    -0.05
    POSITIVE LOGITS
    edral
    0.07
    obus
    0.06
    urity
    0.06
     Anh
    0.06
    .FieldName
    0.06
    defense
    0.06
    щина
    0.06
     meshes
    0.06
     unrest
    0.06
    ians
    0.06
    Act Density 0.135%

    No Known Activations