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

    Neuronpedia

    INDEX
    Explanations

    anti-drug awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anggota
    0.47
    adá
    0.36
     непо
    0.36
     सदस्यों
    0.35
     دسترس
    0.35
     cuối
    0.35
    autre
    0.35
    omos
    0.35
    рк
    0.35
    hos
    0.34
    POSITIVE LOGITS
    ологі
    0.48
     campaigns
    0.42
     campagnes
    0.40
    ্মদ
    0.39
     juggle
    0.38
    πη
    0.37
    ステム
    0.37
     pyautogui
    0.37
    ўнай
    0.36
    クトル
    0.36
    Act Density 0.039%

    No Known Activations