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

    Neuronpedia

    INDEX
    Explanations

    the nature and impact of abstract concepts like knowledge, ideas, circumstances, and influence.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @theofarrell99
    New Auto-Interp
    Negative Logits
    などで
    1.60
     She
    1.58
    または
    1.54
     historians
    1.54
     she
    1.53
    之旅
    1.53
    あるいは
    1.52
    inerary
    1.49
     scheme
    1.48
    She
    1.47
    POSITIVE LOGITS
    rinsic
    2.32
     perceiving
    1.98
     fizik
    1.96
     newfound
    1.87
    7
    1.84
     việc
    1.83
    inguishing
    1.76
     combust
    1.74
     сути
    1.72
     чисто
    1.71
    Act Density 3.818%

    No Known Activations