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

    Neuronpedia

    INDEX
    Explanations

    concepts related to intent, whether malicious or unintentional

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

    intent and inclination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pushFollow
    -0.47
    SpringBootTest
    -0.39
    mjs
    -0.38
    PageData
    -0.38
     descrição
    -0.36
     GreatSchools
    -0.36
    zzleHttp
    -0.36
    jetbrains
    -0.36
    outSlope
    -0.35
    Eres
    -0.35
    POSITIVE LOGITS
     intention
    0.67
     intent
    0.66
     intentions
    0.57
     humeur
    0.56
     настроение
    0.55
     disposition
    0.55
    disposition
    0.54
    StoryboardSegue
    0.54
     inclined
    0.53
     disposed
    0.52
    Act Density 0.104%

    No Known Activations