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

    Neuronpedia

    INDEX
    Explanations

    bash commands or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OSA
    0.46
     Writing
    0.45
     Grecia
    0.45
    NavItem
    0.44
     Wiel
    0.41
    危机
    0.41
    禟
    0.41
     writing
    0.41
    帔
    0.41
     ஒன்று
    0.41
    POSITIVE LOGITS
    命令
    0.40
     命令
    0.39
    libexec
    0.38
    apter
    0.37
    捧
    0.37
     icons
    0.37
     आइकन
    0.37
    コマンド
    0.36
    جهزة
    0.36
    ༤
    0.36
    Act Density 0.001%

    No Known Activations