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

    Neuronpedia

    INDEX
    Explanations

    mental health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    renti
    0.66
     לפ
    0.65
    INDOW
    0.65
     वारदात
    0.63
     draftsman
    0.63
    ypse
    0.59
    Window
    0.59
    ုန်း
    0.59
     თან
    0.58
    rington
    0.56
    POSITIVE LOGITS
     health
    5.53
    health
    5.09
     Health
    5.05
    Health
    5.01
    健康
    4.70
     HEALTH
    4.54
     स्वास्थ्य
    4.27
    HEALTH
    4.25
     건강
    4.17
     saúde
    4.16
    Act Density 0.608%

    No Known Activations