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

    Neuronpedia

    INDEX
    Explanations

    designation, ID, or label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.55
     alligator
    0.47
     XOR
    0.45
    流程
    0.44
    zyma
    0.42
    details
    0.40
    ebel
    0.39
     reusable
    0.39
    ↵↵
    0.39
    document
    0.39
    POSITIVE LOGITS
     संबोध
    0.49
     magnification
    0.48
     mockery
    0.46
     Counselling
    0.45
    耺
    0.45
     preached
    0.44
    പറ
    0.44
     Bezeichnung
    0.44
     counsell
    0.43
     называют
    0.43
    Act Density 0.005%

    No Known Activations