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

    Neuronpedia

    INDEX
    Explanations

    high-risk activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الفرنسي
    0.56
     alimentation
    0.55
     pavimento
    0.53
     ему
    0.53
     খাদ্য
    0.53
     inox
    0.53
     alte
    0.52
     hrane
    0.52
     fixe
    0.51
     Vgl
    0.51
    POSITIVE LOGITS
    。
    0.55
    ിട
    0.51
    *
    0.51
    ا۔
    0.48
    rés
    0.46
    Wikimedia
    0.44
    Secondary
    0.43
    enn
    0.42
    "。
    0.42
    Sis
    0.42
    Act Density 0.000%

    No Known Activations