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

    Neuronpedia

    INDEX
    Explanations

    metaphorical attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     др
    0.51
     perceive
    0.44
     Integrated
    0.43
     characterize
    0.43
     simplify
    0.41
     !",
    0.41
     perspici
    0.40
     bewusst
    0.40
     initially
    0.40
     RetValue
    0.40
    POSITIVE LOGITS
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.79
     lmao
    0.75
    Apparently
    0.74
     apparently
    0.72
     Apparently
    0.72
    apparently
    0.64
     BECAUSE
    0.64
     lest
    0.63
     hilarious
    0.61
    ?!?!
    0.61
    Act Density 0.173%

    No Known Activations