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

    Neuronpedia

    INDEX
    Explanations

    strong adjectives and adverbs that indicate intensity or closeness

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

    describing strength of connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    preuves
    -0.30
    Simulated
    -0.27
     sür
    -0.27
    scriber
    -0.27
    ₁)
    -0.26
    vician
    -0.25
    CodedInputStream
    -0.25
     administrar
    -0.25
    Meanwhile
    -0.25
    Sommer
    -0.24
    POSITIVE LOGITS
     MaterialApp
    0.60
    ſicht
    0.59
     ddelwed
    0.59
    (!__
    0.58
     EconPapers
    0.58
     Paglinawan
    0.57
    PMailer
    0.57
    ſſung
    0.57
    httphttps
    0.57
     zwiſchen
    0.56
    Act Density 0.048%

    No Known Activations