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

    Neuronpedia

    INDEX
    Explanations

    topics that stimulate critical thinking and discussion

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

    discussion prompts or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    riwal
    -0.50
     dAtA
    -0.45
     AssemblyCompany
    -0.41
     bpy
    -0.40
     Infórmanos
    -0.38
    webElementXpaths
    -0.37
    \{\\
    -0.37
    ❉
    -0.36
     TestBed
    -0.36
    igation
    -0.35
    POSITIVE LOGITS
    provoking
    0.65
     intriguing
    0.57
     provocative
    0.56
    discussion
    0.53
     prompts
    0.53
     provoking
    0.50
     GenerationType
    0.50
    discussions
    0.50
     discussão
    0.49
     prompt
    0.48
    Act Density 0.058%

    No Known Activations