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

    Neuronpedia

    INDEX
    Explanations

    phrase structures indicating contrast or comparison between two sides

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

    on the one hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormState
    -0.39
    nefs
    -0.34
    kyou
    -0.34
     Codable
    -0.32
     chambers
    -0.32
     Domes
    -0.32
     carc
    -0.32
     déb
    -0.31
    sibilities
    -0.31
    Tracce
    -0.31
    POSITIVE LOGITS
     einerseits
    0.90
    一方面
    0.75
    первых
    0.73
     andererseits
    0.70
    另一方面
    0.67
     zwar
    0.57
    UnusedPrivate
    0.57
    SequentialGroup
    0.55
     Firstly
    0.54
    onora
    0.53
    Act Density 0.013%

    No Known Activations