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

    Neuronpedia

    INDEX
    Explanations

    male names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     standalone
    0.43
     usability
    0.43
     leverages
    0.41
     implementations
    0.40
     specific
    0.40
     caveats
    0.40
     workflows
    0.39
     \"
    0.39
     leveraging
    0.39
    \/}
    0.39
    POSITIVE LOGITS
     Dominic
    0.54
     Quentin
    0.52
     Daniel
    0.51
     Tristan
    0.51
     Dustin
    0.50
    Liam
    0.48
     Noah
    0.48
    Noah
    0.48
     Caleb
    0.48
     Tobias
    0.48
    Act Density 0.032%

    No Known Activations