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

    Neuronpedia

    INDEX
    Explanations

    mentioning specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Question
    0.44
     Choose
    0.43
     Understanding
    0.42
     Abandon
    0.41
     Aboriginal
    0.39
     Answer
    0.38
     Choosing
    0.38
     stellte
    0.38
     answer
    0.38
     Determine
    0.37
    POSITIVE LOGITS
     언급
    0.76
     mention
    0.73
     mentions
    0.69
     mentioning
    0.69
    Mention
    0.67
    mention
    0.65
     जिक्र
    0.63
     mencion
    0.62
     menciona
    0.61
     упомина
    0.60
    Act Density 0.148%

    No Known Activations