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

    Neuronpedia

    INDEX
    Explanations

    int

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    49
    -0.07
    Fra
    -0.07
    mgr
    -0.07
    wort
    -0.07
     chores
    -0.06
     CLI
    -0.06
    /gpl
    -0.06
    Stack
    -0.06
    lobal
    -0.06
     stří
    -0.06
    POSITIVE LOGITS
    <len
    0.06
    บท
    0.06
     neler
    0.06
     �
    0.06
    .health
    0.06
     galer
    0.06
    编辑
    0.06
     tsunami
    0.06
     평당
    0.06
    σον
    0.06
    Act Density 0.045%

    No Known Activations