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

    Neuronpedia

    INDEX
    Explanations

    HTML attributes related to styling and scripting

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

    "= followed by font"

    np_acts-logits-general · gemini-2.0-flash

    font styles and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.75
    iſen
    -0.70
     ſei
    -0.66
     zuſammen
    -0.64
    niſſe
    -0.64
     ſich
    -0.63
     wireType
    -0.63
     ſur
    -0.63
     beſch
    -0.62
     ſte
    -0.62
    POSITIVE LOGITS
    ="
    0.68
    ='
    0.49
    =\"
    0.43
     ="
    0.40
    =
    0.40
    ]="
    0.40
    {~
    0.39
     incluidas
    0.38
    ================
    0.38
    ={
    0.37
    Act Density 0.167%

    No Known Activations