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

    Neuronpedia

    INDEX
    Explanations

    Limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moy
    -0.08
     geben
    -0.08
    례
    -0.07
     Matte
    -0.07
    แท
    -0.07
     возбуж
    -0.07
     Sw
    -0.07
     Joining
    -0.07
     rejoindre
    -0.07
     tara
    -0.07
    POSITIVE LOGITS
     constraints
    0.15
    Constraints
    0.14
     محدود
    0.14
     Constraints
    0.14
     beperkte
    0.14
     limitado
    0.13
     제한
    0.13
    限制
    0.13
     budget
    0.13
     ogranic
    0.13
    Act Density 0.057%

    No Known Activations