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

    Neuronpedia

    INDEX
    Explanations

    terms related to locations or geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    港区, 没编译, 仕切る

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.70
     ſte
    -0.70
     ſtre
    -0.65
     ſtate
    -0.64
     ſtand
    -0.61
     preſent
    -0.60
     faſt
    -0.60
     myſelf
    -0.59
     ſta
    -0.59
     ſou
    -0.58
    POSITIVE LOGITS
     مح
    2.14
     المح
    1.86
    مح
    1.66
     محل
    0.63
     تح
    0.62
     محف
    0.53
     מח
    0.53
     يح
    0.52
     مج
    0.50
    تح
    0.50
    Act Density 0.001%

    No Known Activations