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

    Neuronpedia

    INDEX
    Explanations

    * like * pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     radiographs
    0.52
     optimizations
    0.48
     jewelry
    0.46
     optimizing
    0.46
    workflows
    0.46
    BES
    0.45
     auctions
    0.44
    Seperti
    0.44
     workflows
    0.44
    Then
    0.44
    POSITIVE LOGITS
    ેટ
    0.52
     Donne
    0.48
    אן
    0.48
    хин
    0.47
    ابة
    0.47
     dado
    0.46
     créée
    0.46
    ſelf
    0.46
     rightful
    0.46
    اه
    0.45
    Act Density 0.004%

    No Known Activations