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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to moral or ethical dilemmas and decision-making

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

    then good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    重要的是
    -0.41
    InputTagHelper
    -0.40
    UnusedPrivate
    -0.39
    当たり前
    -0.38
    assertSame
    -0.38
    VIAF
    -0.38
    randomUUID
    -0.37
    なのです
    -0.37
     pab
    -0.37
     predictable
    -0.37
    POSITIVE LOGITS
    richTextPanel
    0.57
     NavController
    0.56
    MemoryWarning
    0.52
     صوتيه
    0.51
     CURLOPT
    0.48
     estekak
    0.47
    SharedDtor
    0.47
    TypedDataSet
    0.46
    AutoScaleMode
    0.45
    MethodManager
    0.45
    Act Density 0.023%

    No Known Activations