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

    Neuronpedia

    INDEX
    Explanations

    This is a tricky question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terbesar
    0.44
     loudest
    0.42
     unthinkable
    0.42
     humility
    0.40
     unimaginable
    0.40
    Conversation
    0.40
     đương
    0.38
     przem
    0.38
    Obviously
    0.38
    responseData
    0.38
    POSITIVE LOGITS
     question
    0.65
     slightly
    0.64
    稍微
    0.61
     surprisingly
    0.61
     tricky
    0.61
     somewhat
    0.60
     Surprisingly
    0.58
     spør
    0.56
     interestingly
    0.55
     decept
    0.55
    Act Density 0.006%

    No Known Activations