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

    Neuronpedia

    INDEX
    Explanations

    reviewing, assessing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     später
    -0.10
     later
    -0.08
     senere
    -0.08
    _LOOP
    -0.07
     the
    -0.07
    står
    -0.07
     فهو
    -0.07
     multiple
    -0.07
     works
    -0.07
     póź
    -0.07
    POSITIVE LOGITS
     aggior
    0.10
    -update
    0.10
     atualização
    0.10
     atualizar
    0.10
    。今年
    0.10
     обнов
    0.10
     अपडेट
    0.10
    前年比
    0.10
    	Update
    0.09
     shortlist
    0.09
    Act Density 0.048%

    No Known Activations