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

    Neuronpedia

    INDEX
    Explanations

    references to showing support or arguments for a cause

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

    "Show" and its variations

    np_acts-logits-general · gemini-2.0-flash

    demonstrating or showing how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     descriptions
    -0.52
     observables
    -0.51
     reports
    -0.48
     utterances
    -0.47
    obao
    -0.47
     zvuky
    -0.47
     description
    -0.46
    Explanation
    -0.46
     wydaje
    -0.46
    +#+#
    -0.46
    POSITIVE LOGITS
     true
    0.87
    Portale
    0.86
     seriousness
    0.83
     مدى
    0.81
     typelib
    0.77
    いかに
    0.76
    true
    0.76
     calendriers
    0.74
    それだけ
    0.74
    clearly
    0.74
    Act Density 0.358%

    No Known Activations