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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     derog
    -0.07
    .fi
    -0.06
    Datos
    -0.06
     unders
    -0.06
    。あ
    -0.06
    ΑΔ
    -0.06
    hawks
    -0.06
    .setObjectName
    -0.06
    "},"
    -0.06
     bathtub
    -0.06
    POSITIVE LOGITS
     adolescent
    0.07
     Term
    0.07
     occasional
    0.07
    -term
    0.07
     Hole
    0.07
    metro
    0.06
     completeness
    0.06
     travel
    0.06
     normalized
    0.06
     cellular
    0.06
    Act Density 0.021%

    No Known Activations