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

    Neuronpedia

    INDEX
    Explanations

    experiencingreportsensitivestealing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonprofits
    0.83
     mamá
    0.79
     loopholes
    0.75
     extremists
    0.74
     landfills
    0.73
     communism
    0.73
     kvůli
    0.73
     traffickers
    0.73
     Außerdem
    0.72
     enemies
    0.70
    POSITIVE LOGITS
    Whilst
    0.84
    ครับ
    0.75
    த்தினை
    0.75
     focussed
    0.71
     весьма
    0.71
    優れた
    0.71
     recognisable
    0.71
    ினை
    0.70
     Whilst
    0.70
    非常に
    0.69
    Act Density 0.000%

    No Known Activations