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

    Neuronpedia

    INDEX
    Explanations

    language related to deceitful or sneaky behavior

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

    furtive design or conspiracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageState
    -0.45
     MessageBoxIcon
    -0.43
    ponge
    -0.43
    lacian
    -0.42
     asist
    -0.39
    komfort
    -0.39
     Mile
    -0.39
    izr
    -0.38
     силь
    -0.38
     levee
    -0.38
    POSITIVE LOGITS
     ivelany
    0.55
    RenderAtEndOf
    0.55
     autorytatywna
    0.54
     ujednoznacz
    0.52
     '\\;'
    0.51
     defaultstate
    0.49
    WriteTagHelper
    0.49
     ligiloj
    0.48
    uxxxx
    0.47
     clandestine
    0.46
    Act Density 0.153%

    No Known Activations