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

    Neuronpedia

    INDEX
    Explanations

    online moderation guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     전망
    -0.10
    Mortgage
    -0.08
    inga
    -0.08
    eloze
    -0.08
     compradores
    -0.08
     comprador
    -0.08
     proiz
    -0.08
     гор
    -0.08
     greenery
    -0.08
     Grocery
    -0.08
    POSITIVE LOGITS
    违规
    0.14
     misconduct
    0.13
    处罚
    0.12
     banning
    0.12
     disciplinary
    0.12
    犯
    0.11
     punitive
    0.11
     punishment
    0.11
     Enforcement
    0.11
    罚
    0.11
    Act Density 0.055%

    No Known Activations