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

    Neuronpedia

    INDEX
    Explanations

    anxiety and mental health conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    3.89
    り
    2.98
    ল
    2.97
    ,}$
    2.97
    м
    2.91
    р
    2.88
     suministro
    2.85
    رے
    2.79
    д
    2.71
    न
    2.70
    POSITIVE LOGITS
    ﻡ
    3.56
    appcompat
    3.40
     దీంతో
    3.35
    यों
    3.24
    𝒗
    3.23
    𝒊
    3.21
     eigenvectors
    3.12
    𝒅
    3.10
    s
    3.09
    𝒙
    3.07
    Act Density 0.074%

    No Known Activations