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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frutas
    -0.08
     stretch
    -0.08
     الأخ
    -0.08
     bestimmen
    -0.08
    _IO
    -0.07
     ذکر
    -0.07
     verkrijgbaar
    -0.07
     listas
    -0.07
     princípios
    -0.07
    _connected
    -0.07
    POSITIVE LOGITS
     appreciate
    0.10
     appreciates
    0.09
     crée
    0.09
     keen
    0.08
     Capit
    0.08
     geli
    0.08
     apprécier
    0.08
    ccoli
    0.08
    欣
    0.08
    -driven
    0.08
    Act Density 0.167%

    No Known Activations