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

    Neuronpedia

    INDEX
    Explanations

    HTML attribute assignments

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

    HTML links and academic references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.40
     accro
    -0.39
     pédagogique
    -0.36
    hyperref
    -0.36
     actionMode
    -0.35
     écrivain
    -0.35
    TextFormField
    -0.35
    annelse
    -0.35
     trésor
    -0.34
     minuten
    -0.34
    POSITIVE LOGITS
     @"/
    0.70
    MessageOf
    0.69
    DockStyle
    0.68
    ValueStyle
    0.65
    +#+#
    0.64
     المعيارى
    0.62
     autorytatywna
    0.61
     snippetHide
    0.60
    Hochspringen
    0.59
    Diweddarwch
    0.58
    Act Density 0.027%

    No Known Activations