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

    Neuronpedia

    INDEX
    Explanations

    themes of symbolism and literary analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     workflows
    0.63
     nonprofits
    0.56
     leveraging
    0.55
     incentivize
    0.55
     optimize
    0.54
     workaround
    0.54
     chipset
    0.54
     downsides
    0.54
     startups
    0.53
     ਤੁਹਾ
    0.53
    POSITIVE LOGITS
     narrator
    0.87
     symbolic
    0.77
    象征
    0.72
     Symbol
    0.71
     symbolically
    0.71
     symbol
    0.70
     Characters
    0.68
     ironic
    0.67
     симво
    0.66
     juxtap
    0.66
    Act Density 0.046%

    No Known Activations