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

    Neuronpedia

    INDEX
    Explanations

    terms related to loss, removal, or decline in various contexts

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

    ending or ceasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.45
     esternos
    -0.40
    WebControls
    -0.40
    IsPostBack
    -0.35
    quels
    -0.35
    adaptiveStyles
    -0.35
    RUnlock
    -0.34
    :+:
    -0.33
     Dap
    -0.32
    Ry
    -0.32
    POSITIVE LOGITS
    GONE
    0.55
     former
    0.54
    Gone
    0.54
     Gone
    0.51
    exitRule
    0.50
     GONE
    0.50
    writeField
    0.50
     Former
    0.49
    Former
    0.48
     discul
    0.48
    Act Density 0.105%

    No Known Activations