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

    Neuronpedia

    INDEX
    Explanations

    /run or run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    滁
    -0.08
     provoked
    -0.08
    efe
    -0.07
     Molly
    -0.07
     nurt
    -0.07
    🌿
    -0.07
     Denise
    -0.07
    ᡌ
    -0.07
     cmb
    -0.07
     filtered
    -0.07
    POSITIVE LOGITS
     goddess
    0.06
    ustrial
    0.06
    帝王
    0.06
    àng
    0.06
    ："
    0.06
    )))));↵
    0.06
     Abilities
    0.06
    Capital
    0.06
    而后
    0.06
     Steel
    0.06
    Act Density 0.001%

    No Known Activations