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

    Neuronpedia

    INDEX
    Explanations

    .random

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     portals
    -0.08
    ⟡
    -0.07
     appear
    -0.07
     bunk
    -0.07
    澥
    -0.07
    [];
↵
    -0.07
     pInfo
    -0.07
    珲
    -0.06
     responseType
    -0.06
     postId
    -0.06
    POSITIVE LOGITS
    ель
    0.08
    raction
    0.08
    oral
    0.07
     Slayer
    0.07
     oak
    0.07
    aka
    0.07
     slavery
    0.07
    _images
    0.07
    tenant
    0.07
     democracy
    0.07
    Act Density 0.001%

    No Known Activations