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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to positive emotions and experiences.

    oai_token-act-pair · gemini-2.0-flash

    positive emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abestanden
    -0.61
     Anſ
    -0.60
    ✭✭
    -0.59
     AssemblyCulture
    -0.59
     transfieras
    -0.56
    ArrowToggle
    -0.55
     himo
    -0.55
    OGND
    -0.54
    tagHelperRunner
    -0.52
     समीक्षाओं
    -0.52
    POSITIVE LOGITS
     and
    0.59
    Enders
    0.58
     in
    0.55
    setViewName
    0.55
    apunov
    0.52
    IActionResult
    0.52
    basicConfig
    0.52
    yarnpkg
    0.52
    ophanes
    0.51
    ":[{
    0.50
    Act Density 6.986%

    No Known Activations