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

    Neuronpedia

    INDEX
    Explanations

    achieving success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imetre
    0.43
     mandrel
    0.40
    oded
    0.39
    হই
    0.38
    odet
    0.38
    াবলীর
    0.37
     intending
    0.36
     SMTP
    0.36
     faults
    0.36
    lič
    0.36
    POSITIVE LOGITS
     attainable
    1.21
     achieved
    1.20
     achievable
    1.19
     attained
    1.13
     elusive
    1.09
     obtainable
    1.02
     attainment
    0.93
     unattainable
    0.90
     attain
    0.89
     achieve
    0.88
    Act Density 0.035%

    No Known Activations