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

    Neuronpedia

    INDEX
    Explanations

    negative feedback and complaints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     studies
    0.75
    grids
    0.70
    graphicx
    0.69
     often
    0.68
    0.68
    studies
    0.65
     as
    0.64
     enthusi
    0.64
     grids
    0.63
    的一些
    0.63
    POSITIVE LOGITS
     disgusted
    1.31
     disgraceful
    1.27
     ruining
    1.25
     deplorable
    1.23
     humiliated
    1.20
    😡
    1.19
     intolerable
    1.17
     outraged
    1.16
     incompetence
    1.16
     disgusting
    1.16
    Act Density 0.532%

    No Known Activations