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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     〉
    -0.08
    >((
    -0.07
    (PRO
    -0.07
    (Network
    -0.07
    [((
    -0.07
    (identity
    -0.07
     ((__
    -0.07
     chooses
    -0.07
     Parents
    -0.06
     Journal
    -0.06
    POSITIVE LOGITS
     살
    0.07
    ┣
    0.06
     psychotic
    0.06
     Mavericks
    0.06
     herbs
    0.06
     contemplating
    0.06
    -Y
    0.06
    authenticated
    0.06
    Neighbors
    0.06
     preparedStatement
    0.06
    Act Density 0.034%

    No Known Activations