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

    Neuronpedia

    INDEX
    Explanations

    giving support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     said
    -0.07
    producer
    -0.07
     containing
    -0.07
     divisions
    -0.07
    각
    -0.06
    уются
    -0.06
    물
    -0.06
     phosphate
    -0.06
    µ
    -0.06
    ('{}
    -0.06
    POSITIVE LOGITS
    !=↵
    0.07
     Sosyal
    0.07
    .ColumnName
    0.06
    .Current
    0.06
    taş
    0.06
    .Module
    0.06
    .appendChild
    0.06
     Eğer
    0.06
    (dialog
    0.06
     DES
    0.06
    Act Density 0.016%

    No Known Activations