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

    Neuronpedia

    INDEX
    Explanations

    elements related to legal discussions and interpretations

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

    Text within brackets

    np_acts-logits-general · gemini-2.0-flash

    bracketed citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tazama
    -0.76
    Vidite
    -0.54
     bio
    -0.52
    operazione
    -0.51
    ellus
    -0.49
     Silber
    -0.48
     Bio
    -0.48
     valid
    -0.45
    punkt
    -0.45
     Aer
    -0.44
    POSITIVE LOGITS
    তথ্যসূত্র
    0.88
     kasarigan
    0.85
    AnimationsModule
    0.78
     itſelf
    0.72
     TPA
    0.65
     leaſt
    0.65
     purpoſe
    0.64
     ſeveral
    0.64
     themſelves
    0.62
    setupUi
    0.62
    Act Density 0.475%

    No Known Activations