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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tor
    0.67
     Tor
    0.62
    Adding
    0.61
     advantage
    0.59
    ˹
    0.57
     Adding
    0.56
     Plas
    0.56
    addNew
    0.55
     adv
    0.55
     TOR
    0.54
    POSITIVE LOGITS
     Struktur
    0.80
    輕
    0.79
     estrutura
    0.76
    ousal
    0.74
     структуры
    0.73
     そこ
    0.73
     strukt
    0.72
    struktur
    0.71
     estructura
    0.71
    льної
    0.71
    Act Density 0.005%

    No Known Activations