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

    Neuronpedia

    INDEX
    Explanations

    Appeals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [](
    -0.07
    Visit
    -0.07
     comercial
    -0.07
    -care
    -0.07
    似乎
    -0.07
     hlavu
    -0.06
    boats
    -0.06
     document
    -0.06
    [w
    -0.06
    ")));↵
    -0.06
    POSITIVE LOGITS
    genes
    0.07
     Norse
    0.07
     affects
    0.07
     innovations
    0.06
     NavLink
    0.06
    ITCH
    0.06
     стар
    0.06
    пор
    0.06
     fChain
    0.06
    ighet
    0.06
    Act Density 0.003%

    No Known Activations