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

    Neuronpedia

    INDEX
    Explanations

    references to harbors or environments associated with water

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

    harbor/harbour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.62
    SuppressLint
    -0.51
     Vicky
    -0.50
     Zayn
    -0.50
    الدراسه
    -0.48
     Dani
    -0.48
     Zwie
    -0.48
    畢
    -0.47
     Bli
    -0.47
     Snake
    -0.47
    POSITIVE LOGITS
     Harbor
    2.28
     harbor
    2.09
     Harbour
    2.08
    Harbor
    2.06
     harbour
    1.88
     harbors
    1.50
    har
    0.94
     Hafen
    0.90
     HAR
    0.88
     bahía
    0.84
    Act Density 0.002%

    No Known Activations