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

    Neuronpedia

    INDEX
    Explanations

    HTML line break and div elements

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

    HTML tags and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.53
     صوتيه
    -0.49
     rowspan
    -0.46
     الرياضيه
    -0.44
    Personendaten
    -0.43
    новниш
    -0.43
    '):
    -0.43
     propOrder
    -0.42
    adaptiveStyles
    -0.42
     Normdatei
    -0.41
    POSITIVE LOGITS
     rodilla
    0.41
    akterysty
    0.41
    /******/
    0.41
    sproz
    0.40
     burbuja
    0.40
     logique
    0.40
     &___
    0.40
    SEGUIR
    0.39
     Brüder
    0.39
    Bakgrunnsstoff
    0.39
    Act Density 0.002%

    No Known Activations