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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating definitions or explanations of terms and concepts

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

    second method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.79
     kasarigan
    -0.69
    GEBURTSDATUM
    -0.68
    Autoritní
    -0.66
    +:+
    -0.58
    OGND
    -0.57
     виправивши
    -0.57
    niſſe
    -0.54
    сылкі
    -0.52
     queſta
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    0.42
     onderwijs
    0.31
     ži
    0.30
    ValueStyle
    0.29
     slaap
    0.29
    bleven
    0.29
    prende
    0.28
    fjspx
    0.28
     bolsos
    0.27
     verkoop
    0.27
    Act Density 0.054%

    No Known Activations