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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     safari
    -0.07
    pole
    -0.06
     Sheldon
    -0.06
     hisset
    -0.06
     طور
    -0.06
     roam
    -0.06
     �
    -0.06
    “What
    -0.06
     Remix
    -0.06
     polit
    -0.06
    POSITIVE LOGITS
     ک
    0.07
     funds
    0.07
     �
    0.06
    material
    0.06
     SOURCE
    0.06
    Anti
    0.06
     �
    0.06
    .Month
    0.06
    .cleanup
    0.06
     Lum
    0.06
    Act Density 0.018%

    No Known Activations