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

    Neuronpedia

    INDEX
    Explanations

    core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alexandra
    -0.09
     النه
    -0.08
     नेट
    -0.08
     راحت
    -0.08
     зл
    -0.08
     TPS
    -0.08
    কাৰ
    -0.08
    тал
    -0.08
    _AGENT
    -0.08
     genial
    -0.08
    POSITIVE LOGITS
     essentials
    0.07
     essenciais
    0.07
    統
    0.07
     scripting
    0.07
     glue
    0.07
    Plus
    0.07
     Plus
    0.07
     fundamentais
    0.07
     اسرائی
    0.07
    �
    0.07
    Act Density 0.006%

    No Known Activations