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

    Neuronpedia

    INDEX
    Explanations

    descriptive classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ried
    0.45
     gott
    0.42
    default
    0.37
     default
    0.36
     composers
    0.36
     isoform
    0.35
     chaired
    0.35
     prefab
    0.35
     soziale
    0.35
     نمبر
    0.35
    POSITIVE LOGITS
    ADN
    0.38
    targetReference
    0.37
    पटा
    0.37
    াজের
    0.36
    ذی
    0.36
     NCA
    0.36
    পুরের
    0.35
    لح
    0.35
    ставки
    0.34
    汁
    0.34
    Act Density 0.000%

    No Known Activations