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

    Neuronpedia

    INDEX
    Explanations

    Japanese language snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     debilitating
    1.54
     wealthy
    1.50
     dodgy
    1.46
     endearing
    1.46
     burgeoning
    1.46
     divergents
    1.45
     ghostly
    1.44
     tangy
    1.43
     contentious
    1.43
     serveur
    1.42
    POSITIVE LOGITS
    と
    2.19
    な
    2.06
    が
    2.05
    か
    2.02
    水
    2.02
    最
    2.01
    一
    2.00
    その
    1.99
    用
    1.98
    ハ
    1.95
    Act Density 0.013%

    No Known Activations