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

    Neuronpedia

    INDEX
    Explanations

    for business or travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Champion
    0.50
    Alpes
    0.50
    لاث
    0.48
    Mobil
    0.48
    الصفحه
    0.47
    Premi
    0.47
    Kinds
    0.47
    Productos
    0.47
    Obl
    0.47
    Romeo
    0.46
    POSITIVE LOGITS
     nhưng
    0.54
    aba
    0.53
     поскольку
    0.52
    oc
    0.51
    eta
    0.50
    ptr
    0.50
    ker
    0.49
     glyphosate
    0.49
    ari
    0.49
     PFAS
    0.49
    Act Density 0.004%

    No Known Activations