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

    Neuronpedia

    INDEX
    Explanations

    references to previously unseen or unpublished works

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

    unprecedented or previously unknown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.39
    golang
    -0.35
     sahibi
    -0.35
    明明
    -0.34
     unit
    -0.33
    brainly
    -0.33
    uttosto
    -0.32
     quienes
    -0.32
     rédaction
    -0.32
     Ansprechpartner
    -0.31
    POSITIVE LOGITS
     unseen
    0.94
     unheard
    0.84
     inéd
    0.82
     unreleased
    0.73
     unpublished
    0.69
     unprecedented
    0.65
     unknown
    0.60
    WebServlet
    0.60
     iné
    0.58
    unpublished
    0.57
    Act Density 0.027%

    No Known Activations