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

    Neuronpedia

    INDEX
    Explanations

    Kubernetes manifests and configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱮ
    -0.78
    ඡ
    -0.77
     FW
    -0.77
    ürgen
    -0.76
    ự
    -0.75
    ﭘ
    -0.75
    Эк
    -0.74
     pana
    -0.74
    されると
    -0.73
    ellido
    -0.73
    POSITIVE LOGITS
     manifest
    0.88
    manif
    0.82
     Manifest
    0.82
    manifest
    0.81
     Strategic
    0.81
     patch
    0.78
     manifestation
    0.78
     manifesting
    0.77
     obtenu
    0.77
    Manifest
    0.76
    Act Density 0.033%

    No Known Activations