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

    Neuronpedia

    INDEX
    Explanations

    extracting text content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Indust
    0.43
    ຊ
    0.43
    Thunder
    0.43
    нії
    0.40
    exploration
    0.38
    MenuItem
    0.38
    Licensed
    0.37
    vate
    0.37
    INDUST
    0.37
    놁
    0.37
    POSITIVE LOGITS
    attrs
    0.70
    prett
    0.60
     attrs
    0.59
     contents
    0.50
     extracted
    0.46
     prett
    0.46
     bello
    0.44
     previous
    0.43
     attributes
    0.41
    decompose
    0.41
    Act Density 0.008%

    No Known Activations