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

    Neuronpedia

    INDEX
    Explanations

    words related to methods or processes involving pathways or routes

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

    roads and paths or a bearer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.63
     &___
    -0.52
    twimg
    -0.49
    +#+#
    -0.45
    contentLoaded
    -0.45
    zugehen
    -0.44
     HttpNotFound
    -0.44
    WebServlet
    -0.43
    Espèce
    -0.43
    WireFormatLite
    -0.40
    POSITIVE LOGITS
    ways
    1.52
    WAYS
    1.00
    Ways
    0.81
     Ways
    0.67
    ophores
    0.64
    ophore
    0.60
     Always
    0.59
     always
    0.59
    Demografía
    0.58
    always
    0.57
    Act Density 0.009%

    No Known Activations