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

    Neuronpedia

    INDEX
    Explanations

    catching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    βολή
    -0.07
    ьв
    -0.07
     hail
    -0.07
    oriented
    -0.06
    ость
    -0.06
     арх
    -0.06
     gereken
    -0.06
    "url
    -0.06
     бать
    -0.06
    она
    -0.06
    POSITIVE LOGITS
    154
    0.07
     přem
    0.06
     bullpen
    0.06
     وصلات
    0.06
    103
    0.06
    Verified
    0.06
    inclusive
    0.06
     bankers
    0.06
    招
    0.06
    听
    0.06
    Act Density 0.001%

    No Known Activations