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

    Neuronpedia

    INDEX
    Explanations

    reviewing or explaining concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boil
    0.39
     Z
    0.37
     parcel
    0.36
     hosting
    0.36
    abol
    0.35
     ventilation
    0.35
     profiles
    0.35
     parcels
    0.35
     asexual
    0.35
     Lawson
    0.34
    POSITIVE LOGITS
     حمایت
    0.42
    牍
    0.41
     espan
    0.40
    քում
    0.40
    晠
    0.39
    وپ
    0.39
    indeterminate
    0.39
    proc
    0.38
    kung
    0.38
     Nevertheless
    0.38
    Act Density 0.000%

    No Known Activations