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

    Neuronpedia

    INDEX
    Explanations

    are you alright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungkinan
    0.43
     ولو
    0.43
    ♗
    0.43
    ക്കേണ്ട
    0.41
    的可能性
    0.39
    indsight
    0.39
    小物
    0.39
     घटनाओं
    0.38
     ως
    0.38
    Situ
    0.38
    POSITIVE LOGITS
     ready
    0.56
     hiding
    0.52
     allergic
    0.52
     admiring
    0.50
     spies
    0.50
     Ready
    0.49
     stealth
    0.49
     Alright
    0.49
     alright
    0.48
     allergies
    0.48
    Act Density 0.008%

    No Known Activations