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

    Neuronpedia

    INDEX
    Explanations

    male given names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     masterpiece
    0.30
    Include
    0.29
    Sensor
    0.29
    损坏
    0.28
     /
    0.28
    )+
    0.28
    Sweep
    0.28
     gradation
    0.27
    Damage
    0.27
     डेंगू
    0.27
    POSITIVE LOGITS
     David
    0.49
     Michael
    0.48
     Jonathan
    0.47
     Peter
    0.46
     Kevin
    0.45
     Daniel
    0.44
     Richard
    0.44
     Robert
    0.43
     Stephen
    0.43
     Ian
    0.42
    Act Density 0.019%

    No Known Activations