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

    Neuronpedia

    INDEX
    Explanations

    distinct from others or not explicitly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     welcomes
    0.50
     Claims
    0.45
     నుండి
    0.45
    reya
    0.45
     Listening
    0.45
     Enquiry
    0.44
     Compatibility
    0.44
     isLoggedIn
    0.43
    槤
    0.43
     Disclosure
    0.43
    POSITIVE LOGITS
    ת
    0.54
    𝘁
    0.53
    ной
    0.52
    িও
    0.52
    ん
    0.52
    т
    0.49
    ן
    0.49
    தொ
    0.49
    ты
    0.48
     других
    0.48
    Act Density 0.002%

    No Known Activations