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

    Neuronpedia

    INDEX
    Explanations

    sense of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spelling
    0.37
     behavior
    0.36
     redirection
    0.35
    ଼
    0.35
     certifications
    0.33
    Behavior
    0.33
    意识
    0.33
     Behavior
    0.32
     mindset
    0.32
     выгляд
    0.32
    POSITIVE LOGITS
     sensação
    0.59
     sensación
    0.58
     gevoel
    0.54
     accomplishment
    0.52
     чувство
    0.52
     perasaan
    0.51
     Gefühl
    0.50
     connectedness
    0.49
     feel
    0.48
     belonging
    0.47
    Act Density 0.048%

    No Known Activations