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

    Neuronpedia

    INDEX
    Explanations

    numbers/emojis following text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OVE
    0.54
     mà
    0.50
     brind
    0.48
    velte
    0.47
     rivel
    0.46
    ifically
    0.46
     naut
    0.46
    侍
    0.45
     cụ
    0.45
     cho
    0.44
    POSITIVE LOGITS
    grams
    0.47
    id
    0.46
    стта
    0.45
    Legisl
    0.43
     технология
    0.43
     hosszú
    0.42
     долго
    0.42
    estion
    0.42
    long
    0.41
    mining
    0.41
    Act Density 0.000%

    No Known Activations