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

    Neuronpedia

    INDEX
    Explanations

    instances of contrasting situations or conditions

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

    followed by question words or punctuation

    np_acts-logits-general · gemini-2.0-flash

    syntax and grammar rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLI
    -0.56
    UnusedPrivate
    -0.48
    AddTagHelper
    -0.46
     provision
    -0.44
    AndroidJUnit
    -0.43
     Provision
    -0.42
     setPassword
    -0.41
    medriver
    -0.40
     doInBackground
    -0.40
     mondeo
    -0.40
    POSITIVE LOGITS
     distinción
    0.44
    canestro
    0.43
     subtle
    0.42
     sutil
    0.42
     contextes
    0.41
     écrivain
    0.41
     honneur
    0.40
    middels
    0.40
     kullanım
    0.40
     usos
    0.39
    Act Density 0.809%

    No Known Activations