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

    Neuronpedia

    INDEX
    Explanations

    negative self-perception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aggreg
    0.39
    denoted
    0.38
     consag
    0.38
     pouls
    0.38
    हून
    0.38
    ayev
    0.37
     eponym
    0.37
     interoper
    0.37
    unehm
    0.37
     denoted
    0.36
    POSITIVE LOGITS
     negative
    1.00
     perfection
    0.96
     нега
    0.96
     procrastination
    0.95
     Perfection
    0.93
     Negative
    0.90
     negativity
    0.90
     नकारात्मक
    0.90
    Negative
    0.89
     sabot
    0.89
    Act Density 0.135%

    No Known Activations