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

    Neuronpedia

    INDEX
    Explanations

    the phrase "help but"

    oai_token-act-pair · gemini-2.0-flash

    cannot help but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.60
    StoryboardSegue
    -0.53
    aarrggbb
    -0.53
     personnalisées
    -0.52
    enderror
    -0.50
    曖昧さ回避
    -0.50
    antd
    -0.49
     Paglinawan
    -0.49
     AssemblyTitle
    -0.47
     fournis
    -0.47
    POSITIVE LOGITS
    NameInMap
    0.58
    ValueGeneration
    0.54
     Transmitter
    0.52
    ustimmung
    0.49
     being
    0.48
     Salute
    0.47
     olev
    0.47
     uncomment
    0.46
     Crespo
    0.46
     celebrating
    0.45
    Act Density 2.812%

    No Known Activations