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

    Neuronpedia

    INDEX
    Explanations

    Dune conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sentences
    -0.08
     summertime
    -0.08
     retrofit
    -0.07
    Sentence
    -0.07
    停止
    -0.07
     marche
    -0.07
    URLConnection
    -0.07
     matched
    -0.07
    -0.07
    Vertices
    -0.07
    POSITIVE LOGITS
     სადაც
    0.09
     Jedi
    0.09
     Fantasy
    0.09
     prophetic
    0.09
     kwis
    0.09
     mystical
    0.08
     Hydraulic
    0.08
    ...",
    0.08
    …"
    0.08
     জায়
    0.08
    Act Density 0.002%

    No Known Activations