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

    Neuronpedia

    INDEX
    Explanations

    montañas de la locura

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     چاہی
    0.50
     comunic
    0.47
     Electrons
    0.47
    tFileInputExcel
    0.47
    িয়া
    0.46
    olí
    0.46
    кистон
    0.45
    raulic
    0.45
     تلوار
    0.45
     núi
    0.45
    POSITIVE LOGITS
    6
    0.69
    1
    0.63
    5
    0.63
    Se
    0.57
    7
    0.57
    4
    0.56
     was
    0.55
    HD
    0.55
    K
    0.54
     reinsurance
    0.53
    Act Density 0.000%

    No Known Activations