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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "then."

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

    what happened since then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    currently
    -0.44
    beutel
    -0.44
     currently
    -0.44
    目前
    -0.42
     Di
    -0.40
     сейчас
    -0.40
     те
    -0.38
     packet
    -0.38
     Cross
    -0.38
    Bibliograf
    -0.37
    POSITIVE LOGITS
     nahilalakip
    0.69
    Geplaatst
    0.54
    følgelig
    0.52
    UnusedPrivate
    0.51
     архивлан
    0.51
     mergeFrom
    0.51
    SharedDtor
    0.49
     محفوظة
    0.48
    原始内容存档
    0.48
    __(/*!
    0.48
    Act Density 0.008%

    No Known Activations