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

    Neuronpedia

    INDEX
    Explanations

    Mars rovers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เซ
    -0.07
     갖
    -0.06
     auc
    -0.06
    Actualizar
    -0.06
     Hun
    -0.06
    нюю
    -0.06
     condom
    -0.06
    cth
    -0.06
     �
    -0.06
     ओर
    -0.06
    POSITIVE LOGITS
    /services
    0.07
    pj
    0.07
    Detailed
    0.07
    "
↵
↵
↵
    0.06
    alia
    0.06
    (secret
    0.06
    **↵↵
    0.06
    /packages
    0.06
     Britain
    0.06
     rarely
    0.06
    Act Density 0.005%

    No Known Activations