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

    Neuronpedia

    INDEX
    Explanations

    references to online security, particularly involving VPNs and privacy-related topics

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

    open, Open, OPEN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     policiales
    -0.48
    ModelForm
    -0.46
     ModelRenderer
    -0.45
     conferencias
    -0.42
    sizeCache
    -0.41
     daarbij
    -0.41
     gevo
    -0.41
     entornos
    -0.41
    UnitTesting
    -0.41
     voeren
    -0.40
    POSITIVE LOGITS
     Open
    1.23
    Open
    1.13
     OPEN
    1.09
     open
    1.04
    OPEN
    1.00
    setOpen
    0.96
    open
    0.95
     openness
    0.83
     setOpen
    0.82
     откры
    0.75
    Act Density 0.013%

    No Known Activations