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

    Neuronpedia

    INDEX
    Explanations

    Authority actions/delegation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хийх
    -0.08
     trochu
    -0.07
    gsm
    -0.07
     Af
    -0.07
     mà
    -0.07
     தீர
    -0.07
     તે
    -0.07
     vão
    -0.07
     конечно
    -0.07
     లేద
    -0.07
    POSITIVE LOGITS
    了一
    0.08
    牧
    0.08
     JK
    0.08
     katt
    0.08
     আর
    0.07
    旗下
    0.07
     kidnapping
    0.07
     gifting
    0.07
    席
    0.07
    聘
    0.07
    Act Density 0.172%

    No Known Activations