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

    Neuronpedia

    INDEX
    Explanations

    proper nouns associated with specific individuals or entities

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

    names and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -0.68
    /*
    -0.64
    !*\
    -0.57
    assertIn
    -0.54
    Ciri
    -0.54
    setVerticalGroup
    -0.53
    rmtree
    -0.52
     Foster
    -0.50
     ivi
    -0.49
    RenderAtEndOf
    -0.49
    POSITIVE LOGITS
     müş
    0.52
     financeira
    0.51
     definately
    0.51
     cuerdas
    0.50
     Generales
    0.49
     Vecchio
    0.49
     mijne
    0.49
     délib
    0.48
    ElementException
    0.47
     stället
    0.47
    Act Density 0.576%

    No Known Activations