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
     úprav
    -0.07
    (t
    -0.06
    ToFront
    -0.06
     leicht
    -0.06
     Pok
    -0.06
     Biology
    -0.06
     discourse
    -0.06
     august
    -0.06
     Basics
    -0.06
     rede
    -0.06
    POSITIVE LOGITS
    abbo
    0.07
    仙
    0.07
    "'
    0.07
    HOST
    0.06
    redentials
    0.06
     lear
    0.06
    Mine
    0.06
    OUTH
    0.06
    रल
    0.06
    ительной
    0.06
    Act Density 0.262%

    No Known Activations