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

    Neuronpedia

    INDEX
    Explanations

    non-english or organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     depends
    0.53
     Photoshop
    0.50
     value
    0.49
    ព័
    0.48
     invoice
    0.48
     attracts
    0.48
     catalogue
    0.48
     invoicing
    0.48
     purchase
    0.47
     Internet
    0.47
    POSITIVE LOGITS
    どう
    0.49
    無理
    0.44
    我
    0.44
    발
    0.44
    主席
    0.43
    埇
    0.43
    灘
    0.43
    古代
    0.42
    ם
    0.42
    ﺀ
    0.42
    Act Density 0.000%

    No Known Activations