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

    Neuronpedia

    INDEX
    Explanations

    Missouri cities and towns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    產品
    0.39
    产品
    0.38
     ድ
    0.38
    揩
    0.38
    ย์
    0.37
     recourse
    0.37
    producto
    0.36
    riso
    0.36
    voř
    0.36
     sync
    0.36
    POSITIVE LOGITS
    Hun
    0.52
     Kir
    0.47
    Kir
    0.47
     hun
    0.47
     Hannibal
    0.45
     kir
    0.44
    kir
    0.44
     Hun
    0.44
     Marcel
    0.44
     Macon
    0.44
    Act Density 0.001%

    No Known Activations