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

    Neuronpedia

    INDEX
    Explanations

    list of professions and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caveats
    0.39
     benefits
    0.38
     boundaries
    0.38
    batas
    0.35
    <start_of_image>
    0.34
    Contemporary
    0.34
     Contemporary
    0.33
     Benefits
    0.33
     Delt
    0.33
    pletion
    0.32
    POSITIVE LOGITS
     songwriter
    0.97
     entrepreneur
    0.93
     philanthropist
    0.90
     philosopher
    0.90
     businessman
    0.89
     poet
    0.88
     musician
    0.88
     educator
    0.84
     writer
    0.84
     adventurer
    0.80
    Act Density 0.007%

    No Known Activations