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

    Neuronpedia

    INDEX
    Explanations

    instances of specific word endings or suffixes

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

    vector geometry, tangent, radii

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.60
     contextLoads
    -0.57
     propOrder
    -0.57
    verwijspagina
    -0.57
     houſe
    -0.56
     betrek
    -0.55
     uſed
    -0.55
    étoit
    -0.55
    OCCURRED
    -0.54
    LEGGI
    -0.52
    POSITIVE LOGITS
    TypedDataSet
    0.54
    ISHOP
    0.40
     Coulson
    0.39
     physically
    0.39
     Corbin
    0.39
    世話
    0.38
    oms
    0.38
    àm
    0.38
     Physically
    0.37
     concurrently
    0.36
    Act Density 0.005%

    No Known Activations