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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to directions or locations

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

    direction or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ciclop
    -0.43
    /*"
    -0.42
     متعلقه
    -0.40
     anys
    -0.40
     Addis
    -0.37
     Процитовано
    -0.37
    #"
    -0.37
    ³)
    -0.36
    ]+\
    -0.36
    \"\
    -0.35
    POSITIVE LOGITS
    こちら
    2.03
    こちらの
    1.69
    こちらは
    1.57
    こっち
    1.56
    そちら
    1.50
     こちら
    1.48
    こちらが
    1.44
    コチラ
    1.41
    こちらも
    1.26
    はこちら
    1.19
    Act Density 0.005%

    No Known Activations