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

    Neuronpedia

    INDEX
    Explanations

    negative feelings, annoyance, inconvenience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     כת
    0.85
    Conditional
    0.85
    Beyond
    0.84
    शब्द
    0.84
     форму
    0.80
     संरचना
    0.80
    setLayout
    0.78
    emberg
    0.76
     ہندو
    0.76
     coloquei
    0.76
    POSITIVE LOGITS
     annoying
    1.75
     inconvenience
    1.75
     misery
    1.68
     delightful
    1.62
     inconven
    1.61
     miserable
    1.59
     annoy
    1.56
     pesky
    1.54
     annoyance
    1.53
     enjoy
    1.52
    Act Density 0.144%

    No Known Activations