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

    Neuronpedia

    INDEX
    Explanations

    incidents or occurrences related to events or actions

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

    in the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.57
     CreateTagHelper
    -0.51
    TabStop
    -0.39
    |')
    -0.35
    HtmlAttribute
    -0.35
    UseVisualStyle
    -0.34
    '}),
    -0.33
     Dostupné
    -0.33
    AddTagHelper
    -0.33
     Савез
    -0.31
    POSITIVE LOGITS
     threatens
    0.52
     threatening
    0.52
     AFFECT
    0.51
     Affecting
    0.51
    threatening
    0.51
     contaminación
    0.50
     lagerfeld
    0.50
    brakk
    0.50
     afect
    0.50
    trouble
    0.50
    Act Density 0.122%

    No Known Activations