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

    Neuronpedia

    INDEX
    Explanations

    references to various institutes

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

    names of institutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rubber
    -0.49
    pregnant
    -0.48
    Babylon
    -0.48
    Mary
    -0.48
    wedding
    -0.48
    cotton
    -0.48
    Wedding
    -0.48
     scorso
    -0.47
    naked
    -0.47
    Haem
    -0.47
    POSITIVE LOGITS
     Institute
    2.09
     institute
    1.88
    Institute
    1.86
     INSTITUTE
    1.76
    institute
    1.55
     institutes
    1.42
     Institutes
    1.37
     Instituto
    1.15
     Institut
    1.09
     instituto
    1.04
    Act Density 0.005%

    No Known Activations