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

    Neuronpedia

    INDEX
    Explanations

    periodic or sequential growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jour
    0.38
    നില്‍
    0.38
     screening
    0.38
     inti
    0.38
    离
    0.38
     Forum
    0.37
     нада
    0.37
     Off
    0.37
    璺
    0.37
     offence
    0.36
    POSITIVE LOGITS
    ოლოგი
    0.50
    스는
    0.47
    臓
    0.47
    ウイルス
    0.46
    なった
    0.46
     प्रिंसिपल
    0.46
    логии
    0.45
     escrib
    0.44
    生まれた
    0.44
    ρού
    0.44
    Act Density 0.001%

    No Known Activations