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

    Neuronpedia

    INDEX
    Explanations

    complex reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     historian
    -0.07
     submodule
    -0.07
    िवस
    -0.07
    ioni
    -0.06
    rego
    -0.06
    Mate
    -0.06
     theo
    -0.06
    іння
    -0.06
    overs
    -0.06
     Quotes
    -0.06
    POSITIVE LOGITS
    .Card
    0.07
     дал
    0.06
     incom
    0.06
    /misc
    0.06
    Atoms
    0.06
     καν
    0.06
     nước
    0.06
     الاع
    0.06
    <Path
    0.06
     pageNum
    0.06
    Act Density 0.211%

    No Known Activations