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

    Neuronpedia

    INDEX
    Explanations

    AI Chatbot disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mixers
    0.69
    mon
    0.69
     Tew
    0.69
    ieniem
    0.69
    慜
    0.68
    мон
    0.67
     sumo
    0.67
     logística
    0.67
    umon
    0.66
     kum
    0.66
    POSITIVE LOGITS
    Connections
    0.85
     Connections
    0.84
    PS
    0.76
     connections
    0.72
    SEP
    0.71
    LS
    0.71
     ETS
    0.66
    connections
    0.66
     SEP
    0.64
     CONNE
    0.64
    Act Density 0.105%

    No Known Activations