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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or comparison

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

    contrasting alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.58
    хьтан
    -0.58
     '\\;'
    -0.58
    IndentedString
    -0.57
     يتيمه
    -0.56
    AddTagHelper
    -0.54
    tvguidetime
    -0.52
    MLLoader
    -0.52
    OGND
    -0.51
    IUrlHelper
    -0.51
    POSITIVE LOGITS
     назвать
    0.40
     uniquely
    0.40
     ạ
    0.39
    単
    0.38
     introducir
    0.38
     conforman
    0.37
     proprement
    0.36
     simply
    0.36
     plainte
    0.36
     saurait
    0.36
    Act Density 0.011%

    No Known Activations