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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey rules or prohibitions

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

    what not to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.62
    ValueStyle
    -0.54
    principalColumn
    -0.49
     myſelf
    -0.48
    AddTagHelper
    -0.48
     Copies
    -0.44
     wußte
    -0.44
    الحياه
    -0.44
    BitmapFactory
    -0.44
    /**
    -0.43
    POSITIVE LOGITS
     ffilmiau
    0.42
    makeConstraints
    0.40
     things
    0.35
    Enllaces
    0.35
     téléphonique
    0.35
    opho
    0.34
     exemplos
    0.34
    StoryboardSegue
    0.33
    teira
    0.33
    LabelTagHelper
    0.33
    Act Density 0.048%

    No Known Activations