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

    Neuronpedia

    INDEX
    Explanations

    scientific publications and research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хозя
    -0.08
    izo
    -0.07
    ayıp
    -0.07
    iez
    -0.07
    493
    -0.06
    swith
    -0.06
    Unlike
    -0.06
    .social
    -0.06
    InChildren
    -0.06
    š
    -0.06
    POSITIVE LOGITS
    *>::
    0.07
     έ
    0.06
     funny
    0.06
    .commands
    0.06
    で
    0.06
     EXPORT
    0.06
    .controller
    0.06
     alta
    0.06
    AGENT
    0.06
     aque
    0.06
    Act Density 0.017%

    No Known Activations