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

    Neuronpedia

    INDEX
    Explanations

    describing annoyance and frustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Complex
    0.84
     успех
    0.81
    Synthesis
    0.76
     complexe
    0.76
     ধর্ষণ
    0.75
    复杂的
    0.73
    complex
    0.73
    つもり
    0.71
     complex
    0.71
     komplex
    0.71
    POSITIVE LOGITS
     annoyance
    2.72
     annoying
    2.66
     frustrating
    2.34
     annoy
    2.34
     annoyed
    2.24
     irritating
    2.23
     exasper
    2.22
     frustrations
    2.17
     frustration
    2.12
     nuisance
    2.08
    Act Density 0.393%

    No Known Activations