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

    Neuronpedia

    INDEX
    Explanations

    issues related to political suppression and oppression

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

    "1" followed by a digit

    np_acts-logits-general · gemini-2.0-flash

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nloa
    -0.79
    GraphicsUnit
    -0.72
    UVWXYZ
    -0.72
    ffine
    -0.69
    WriteTagHelper
    -0.69
    addCriterion
    -0.68
    InputBorder
    -0.68
    extAlignment
    -0.68
    новништво
    -0.67
    alanta
    -0.67
    POSITIVE LOGITS
    7
    1.08
    6
    1.05
    8
    1.05
    9
    1.03
    5
    1.02
    4
    0.96
    3
    0.93
    0
    0.88
    2
    0.86
    1
    0.80
    Act Density 0.107%

    No Known Activations