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

    Neuronpedia

    INDEX
    Explanations

    pausing or resuming operations or access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     success
    0.55
    success
    0.51
     Success
    0.50
    Success
    0.50
     Every
    0.47
     успех
    0.46
    每個
    0.45
     cada
    0.45
    Every
    0.45
     успеха
    0.44
    POSITIVE LOGITS
     operations
    0.87
    operations
    0.72
     hostilities
    0.69
     normal
    0.67
     дальней
    0.66
     festivities
    0.65
     production
    0.63
     operaciones
    0.63
     normalen
    0.61
     further
    0.61
    Act Density 0.037%

    No Known Activations