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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the well-being and collective benefit of people

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

    quantities of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     circle
    -0.40
     CreateTagHelper
    -0.38
    phere
    -0.37
     mark
    -0.37
     mac
    -0.36
     pe
    -0.35
    complexType
    -0.35
    ništ
    -0.35
     chico
    -0.35
     brush
    -0.34
    POSITIVE LOGITS
     propOrder
    0.65
     Infórmanos
    0.61
     Picchu
    0.58
     esternos
    0.57
    ValueStyle
    0.52
    şört
    0.51
    MessageOf
    0.48
     Protección
    0.48
    dientemente
    0.48
     ligiloj
    0.48
    Act Density 0.085%

    No Known Activations