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

    Neuronpedia

    INDEX
    Explanations

    specific types of buildings and gathering spaces

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

    places and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verhält
    -0.45
     progrès
    -0.42
    ército
    -0.41
     Segurança
    -0.41
     ilusión
    -0.41
    CreateIndex
    -0.40
    parametros
    -0.40
    はじめに
    -0.40
     paroisse
    -0.40
    RegistryLite
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.53
     clubhouse
    0.51
    MLLoader
    0.51
     pavilion
    0.49
     Clubhouse
    0.49
    astify
    0.48
     pleaſure
    0.47
    ArrowToggle
    0.46
     Chwiliwch
    0.46
     Pavilion
    0.44
    Act Density 0.014%

    No Known Activations