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

    Neuronpedia

    INDEX
    Explanations

    details about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somew
    0.36
    යෙන්
    0.35
     Something
    0.32
     something
    0.31
    something
    0.31
    もので
    0.31
     etwas
    0.30
     mu
    0.30
    何か
    0.30
    mu
    0.30
    POSITIVE LOGITS
     tentang
    0.80
     about
    0.77
     về
    0.75
     mengenai
    0.73
     regarding
    0.70
    關於
    0.70
    关于
    0.67
     apie
    0.65
     acerca
    0.64
     kuhusu
    0.64
    Act Density 0.023%

    No Known Activations