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

    Neuronpedia

    INDEX
    Explanations

    bot commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chat
    0.52
     Chat
    0.52
     chat
    0.52
    chat
    0.52
     chats
    0.52
    Slack
    0.49
     Slack
    0.48
     IRC
    0.47
    ChatMessage
    0.47
    slack
    0.46
    POSITIVE LOGITS
     Comando
    0.57
     comando
    0.55
     command
    0.53
     команда
    0.51
    命令
    0.50
    コマンド
    0.49
     COMMAND
    0.48
     comand
    0.48
    comando
    0.48
     perintah
    0.48
    Act Density 0.016%

    No Known Activations