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

    Neuronpedia

    INDEX
    Explanations

    references to interdependence and relational dynamics

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

    interposition, some, squarely, new, potential, work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h1>
    -0.52
    <strong>
    -0.42
      
    -0.42
    2
    -0.41
    
    -0.39
    Der
    -0.37
    　
    -0.37
    name
    -0.36
     also
    -0.36
    test
    -0.36
    POSITIVE LOGITS
    NameInMap
    0.84
    MLLoader
    0.68
    AddHtmlAttribute
    0.68
     utafitiHapana
    0.67
     informée
    0.67
    Personendaten
    0.64
     Wikimedijinoj
    0.64
     صوتيه
    0.63
    httphttps
    0.63
    ]")]
    0.62
    Act Density 0.061%

    No Known Activations