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

    Neuronpedia

    INDEX
    Explanations

    measurement units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     này
    -0.08
     copp
    -0.08
     Coff
    -0.08
     khác
    -0.07
     corre
    -0.07
     cure
    -0.07
     SAE
    -0.07
    access
    -0.07
     griff
    -0.07
     access
    -0.07
    POSITIVE LOGITS
     articulated
    0.07
     થશે
    0.07
     У
    0.07
    У
    0.07
    0.07
    Standing
    0.07
     ಹೇಳ
    0.07
    Statements
    0.07
    utile
    0.07
    ust
    0.07
    Act Density 0.049%
    No Known Activations