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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Compound
    -0.06
    Tree
    -0.06
     Boo
    -0.06
    �
    -0.06
     đô
    -0.06
    μένοι
    -0.06
    abit
    -0.06
     aprender
    -0.06
    agine
    -0.06
     но
    -0.06
    POSITIVE LOGITS
    <typename
    0.07
     nejvyšší
    0.07
     Leaving
    0.07
    ,%
    0.06
    getMethod
    0.06
     Wie
    0.06
     innoc
    0.06
    -before
    0.06
    _MA
    0.06
    awy
    0.06
    Act Density 0.152%

    No Known Activations