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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and political discourse

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

    contrast or opposition

    np_acts-logits-general · gemini-2.0-flash

    contrast and opposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ведь
    -0.55
    endphp
    -0.54
     именно
    -0.53
     namelijk
    -0.53
    anglès
    -0.53
    raria
    -0.53
    RectangleBorder
    -0.51
    seigneur
    -0.49
    esgue
    -0.48
    리가
    -0.47
    POSITIVE LOGITS
     meanwhile
    2.33
     hingegen
    1.82
     natomiast
    1.76
     invece
    1.67
     dagegen
    1.53
    Meanwhile
    1.41
     Meanwhile
    1.41
    則
    1.37
    则
    1.35
     kolei
    1.31
    Act Density 0.478%

    No Known Activations