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

    Neuronpedia

    INDEX
    Explanations

    concentration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arth
    -0.08
    Northern
    -0.08
     Duch
    -0.08
     arth
    -0.08
     Bog
    -0.08
    zeit
    -0.08
    দের
    -0.08
    Bog
    -0.07
     рез
    -0.07
     Katherine
    -0.07
    POSITIVE LOGITS
    -aware
    0.08
     vc
    0.08
     eur
    0.07
    ierung
    0.07
    EMP
    0.07
    括
    0.07
     صور
    0.07
     accidental
    0.07
     vase
    0.07
    урда
    0.07
    Act Density 0.007%

    No Known Activations