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

    Neuronpedia

    INDEX
    Explanations

    a/an followed by adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hindrance
    0.41
     coveted
    0.40
     dying
    0.39
     alluring
    0.38
     momentous
    0.38
     continuation
    0.38
     nosso
    0.37
     extremo
    0.37
     suboptimal
    0.37
     midst
    0.36
    POSITIVE LOGITS
    大全
    0.42
    i
    0.41
    gegevens
    0.40
    analyse
    0.39
     Notebook
    0.39
     Paperback
    0.39
     Einige
    0.39
     Lexikon
    0.39
    2
    0.39
    gruppen
    0.38
    Act Density 0.000%

    No Known Activations