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

    Neuronpedia

    INDEX
    Explanations

    India and Indian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㄞ
    2.93
     sitä
    2.67
     vidéo
    2.65
    ꪽ
    2.63
     verdiği
    2.62
     behaving
    2.61
     énon
    2.59
     estés
    2.53
     dériv
    2.50
     sequent
    2.48
    POSITIVE LOGITS
    en
    3.33
    م
    2.74
    voor
    2.71
    यानक
    2.67
    й
    2.61
    ણી
    2.50
    ни
    2.41
    िव
    2.40
    Го
    2.37
    ﮔ
    2.37
    Act Density 0.092%

    No Known Activations