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
     ile
    -0.06
    alizace
    -0.06
    ушки
    -0.06
     disrupt
    -0.06
    ........
    -0.06
     correctamente
    -0.06
    ]))
    -0.06
    	In
    -0.06
     ↘
    -0.06
    _STRUCTURE
    -0.06
    POSITIVE LOGITS
     packet
    0.07
     twin
    0.07
     відч
    0.06
    мерик
    0.06
     Adelaide
    0.06
    =['
    0.06
    NU
    0.06
     Lik
    0.06
    Club
    0.06
     financially
    0.06
    Act Density 0.001%

    No Known Activations