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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional disconnection or apathy

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

    describing apathy or ineffectiveness

    np_acts-logits-general · gemini-2.0-flash

    lack of qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.64
    bootstrapcdn
    -0.63
     nahilalakip
    -0.61
    最快更新
    -0.60
     <",
    -0.59
     CreateTagHelper
    -0.59
     viewDidLoad
    -0.58
     pinulongan
    -0.57
     postIndex
    -0.56
    UserScript
    -0.55
    POSITIVE LOGITS
     inert
    0.86
     lifeless
    0.81
     cold
    0.80
     ap
    0.78
     mute
    0.76
     indifferent
    0.76
     blank
    0.75
     numb
    0.73
     void
    0.72
     voic
    0.71
    Act Density 0.339%

    No Known Activations