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

    Neuronpedia

    INDEX
    Explanations

    end of sentences or punctuation marks

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

    user turn start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MockBean
    -0.51
     onOptions
    -0.48
    enderror
    -0.48
    jména
    -0.43
    tahankan
    -0.42
     '{@
    -0.41
    AddTagHelper
    -0.40
    skjaer
    -0.37
     getClass
    -0.36
     volontaire
    -0.36
    POSITIVE LOGITS
     فريبيس
    0.52
    󠁢
    0.48
     ffilm
    0.48
    ValueGeneration
    0.47
    rrggbb
    0.45
     محفوظة
    0.44
     email
    0.44
     date
    0.43
     विश्वसनीयता
    0.43
     nakalista
    0.43
    Act Density 0.000%

    No Known Activations