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

    Neuronpedia

    INDEX
    Explanations

    street names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     နောက်
    0.43
    empres
    0.41
    cantidad
    0.40
    alker
    0.40
    jenis
    0.39
    biss
    0.39
     ألف
    0.39
     Gosudarstvennyj
    0.39
    estados
    0.38
    eten
    0.38
    POSITIVE LOGITS
     prospect
    0.52
     микро
    0.52
     револю
    0.52
     про
    0.51
     Gag
    0.50
    勝利
    0.50
     revolutionary
    0.50
     героев
    0.49
     Marx
    0.49
     прос
    0.48
    Act Density 0.002%

    No Known Activations