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

    Neuronpedia

    INDEX
    Explanations

    logical connectors and transition words that indicate reasoning or conclusions

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

    Text following "so" or "therefore"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions introducing consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.64
    -0.52
    AndEndTag
    -0.47
     يتيمه
    -0.45
    ➊
    -0.43
     IBOutlet
    -0.43
    BindingSource
    -0.41
    UALA
    -0.40
    retty
    -0.39
    stuff
    -0.39
    POSITIVE LOGITS
     ListTile
    0.41
    ilarang
    0.40
    parsedMessage
    0.39
     cervello
    0.38
     valentín
    0.37
     UIAlert
    0.37
    latego
    0.36
     waste
    0.36
    ENEFITS
    0.35
    ViewChild
    0.35
    Act Density 0.561%

    No Known Activations