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

    Neuronpedia

    INDEX
    Explanations

    asking questions for clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    doesn
    0.47
    should
    0.44
    appropriate
    0.43
    Should
    0.43
     can
    0.43
     should
    0.42
    whatever
    0.42
    needs
    0.42
    proper
    0.41
    serious
    0.41
    POSITIVE LOGITS
     yours
    0.74
     Yours
    0.73
     curioso
    0.70
     curious
    0.68
     Interess
    0.61
     Interestingly
    0.59
     Did
    0.57
     interess
    0.57
     Curious
    0.56
     curios
    0.56
    Act Density 0.006%

    No Known Activations