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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (;;
    -0.07
     Mang
    -0.07
     BMC
    -0.07
    -fired
    -0.07
    .Do
    -0.07
    Forge
    -0.06
    append
    -0.06
     �
    -0.06
     Almighty
    -0.06
    =status
    -0.06
    POSITIVE LOGITS
    Binding
    0.07
     cuff
    0.06
     vm
    0.06
    SEM
    0.06
     Comic
    0.06
    ные
    0.06
     ama
    0.06
     puppy
    0.06
    葉
    0.06
    대한
    0.06
    Act Density 0.002%

    No Known Activations