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

    Neuronpedia

    INDEX
    Explanations

    connections between success and various concepts

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

    promising successful stored containing available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.42
     astore
    -0.32
     which
    -0.32
     is
    -0.31
     where
    -0.28
     brilla
    -0.28
     none
    -0.27
     by
    -0.27
    ..
    -0.27
    none
    -0.26
    POSITIVE LOGITS
     queſta
    0.83
     Houſe
    0.77
     ſte
    0.77
    ſelf
    0.76
     Reſ
    0.76
    leſs
    0.76
     autorytatywna
    0.75
    wiſe
    0.74
    0.73
     Monfieur
    0.72
    Act Density 0.224%

    No Known Activations