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

    Neuronpedia

    INDEX
    Explanations

    same / end / later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الماء
    0.52
     l
    0.47
    efficients
    0.47
     instincts
    0.45
     பே
    0.44
     រ
    0.44
    ugs
    0.44
     زي
    0.44
    modified
    0.44
     Wisconsin
    0.41
    POSITIVE LOGITS
    深度
    0.51
    地に
    0.48
     없이
    0.47
    ೇತ್ರ
    0.46
    anea
    0.45
    ಾಣ
    0.43
    кистон
    0.43
     frequency
    0.43
    requenz
    0.43
    わない
    0.42
    Act Density 0.001%

    No Known Activations