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

    Neuronpedia

    INDEX
    Explanations

    elements related to digital communication and references to online resources

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

    dejal.org URLs and dejuren

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.59
     houſe
    -0.55
     ſta
    -0.54
     ſei
    -0.54
     مشين
    -0.54
     ſte
    -0.54
     kapture
    -0.53
    ſelves
    -0.53
     Eſ
    -0.53
     Efq
    -0.52
    POSITIVE LOGITS
    息
    0.34
     poire
    0.34
    zipped
    0.34
    AuthContext
    0.33
     vel
    0.33
    bus
    0.32
    チー
    0.31
     <
    0.31
    lastIndex
    0.31
     Cracks
    0.31
    Act Density 0.031%

    No Known Activations